WO2022191373A1 - Dispositif électronique et procédé de commande de dispositif électronique - Google Patents

Dispositif électronique et procédé de commande de dispositif électronique Download PDF

Info

Publication number
WO2022191373A1
WO2022191373A1 PCT/KR2021/013997 KR2021013997W WO2022191373A1 WO 2022191373 A1 WO2022191373 A1 WO 2022191373A1 KR 2021013997 W KR2021013997 W KR 2021013997W WO 2022191373 A1 WO2022191373 A1 WO 2022191373A1
Authority
WO
WIPO (PCT)
Prior art keywords
feature points
depth
points
sparse
electronic device
Prior art date
Application number
PCT/KR2021/013997
Other languages
English (en)
Inventor
Christopher Anthony Peri
Yingen Xiong
Original Assignee
Samsung Electronics Co., Ltd.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US17/198,997 external-priority patent/US11688073B2/en
Application filed by Samsung Electronics Co., Ltd. filed Critical Samsung Electronics Co., Ltd.
Publication of WO2022191373A1 publication Critical patent/WO2022191373A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/56—Particle system, point based geometry or rendering

Definitions

  • This disclosure relates generally to database and file management within network environments.
  • this disclosure relates to an electronic device and a controlling method of the electronic device, and in particular, to an electronic device for providing an extended reality system, and a controlling method of the electronic device.
  • An extended reality (XR) system may generally include a computer-generated environment and/or a real-world environment that includes at least some XR artifacts.
  • XR system or world and associated XR artifacts typically include various applications (e.g., video games), which may allow users to utilize these XR artifacts by manipulating their presence in the form of a computer-generated representation (e.g., avatar).
  • image data may be rendered on, for example, a robust head-mounted display (HMD) that may be coupled through a physical wired or wireless connection to a base graphics generation device or cloud based service responsible for generating the image data.
  • HMD head-mounted display
  • the XR glasses or spectacles may, in comparison, include reduced processing power, low-resolution/low-cost cameras, and/or relatively simple tracking optics. Additionally, due to the smaller architectural area, the XR glasses or spectacles may also include reduced power management (e.g., batteries, battery size) and thermal management (e.g., cooling fans, heat sinks) electronics. This may often preclude such devices from maximizing performance while reducing power consumption.
  • reduced power management e.g., batteries, battery size
  • thermal management e.g., cooling fans, heat sinks
  • This disclosure is for addressing the aforementioned need, and the purpose of this disclosure is in providing an electronic device for providing a light-weighted extended reality system, and a controlling method of the electronic device.
  • a controlling method of an electronic device includes the steps of obtaining image data and depth data corresponding to one or more image frames to be displayed on an external device which is associated with the electronic device and for providing extended reality (XR), determining a plurality of sets of feature points corresponding to the one or more image frames based on a multi-layer sampling of the image data and the depth data, generating a set of sparse feature points determined based on relative changes in depth data with respect to the plurality of sets of feature points based on an integration of the plurality of sets of feature points, generating a set of sparse depth points based on the set of sparse feature points and the depth data, and sending the set of sparse depth points to the external device for reconstruction of a dense depth map corresponding to the one or more image frames utilizing the set of sparse depth points.
  • XR extended reality
  • the plurality of sets of feature points may include two or more of a set of object feature points, a set of edge feature points, a set of object contour points, or a set of image contour points.
  • the multi-layer sampling of the image data and the depth data may be performed by extracting the plurality of sets of feature points utilizing two or more of a Difference of Gaussian (DoG) filter, a Laplacian of Gaussian (LoG) filter, a Canny filter, or a Sobel filter.
  • DoG Difference of Gaussian
  • LiG Laplacian of Gaussian
  • the plurality of sets of feature points may be extracted for each of a plurality of scaled representations corresponding to the one or more image frames.
  • the step of generating the set of sparse feature points may include the steps of integrating the plurality of sets of feature points extracted for each of the plurality of scaled representations, and removing a subset of feature points from the integrated plurality of sets of feature points based on relative changes in depth data between the subset of feature points and respective neighboring feature points.
  • the set of sparse depth points may be generated further based on predetermined confidence scores associated with the set of sparse feature points, and each predetermined confidence score may indicate a likelihood the associated feature point corresponds to a determinative feature of the one or more image frames.
  • controlling method may further include the step of sending the image data to the external device, and the dense depth map corresponding to the one or more image frames may be reprojected by the external device based on the set of sparse depth points and the image data.
  • an electronic device includes a memory including instructions, and one or more processors coupled to the memory, the one or more processors configured to, by executing the instructions, obtain image data and depth data corresponding to one or more image frames to be displayed on an extended reality (XR) display device associated with the electronic device, determine a plurality of sets of feature points corresponding to the one or more image frames based on a multi-layer sampling of the image data and the depth data, generate a set of sparse feature points determined based on relative changes in depth data with respect to the plurality of sets of feature points based on an integration of the plurality of sets of feature points, generate a set of sparse depth points based on the set of sparse feature points and the depth data, and send the set of sparse depth points to the external device for reconstruction of a dense depth map corresponding to the one or more image frames utilizing the set of sparse depth points.
  • XR extended reality
  • the plurality of sets of feature points may include two or more of a set of object feature points, a set of edge feature points, a set of object contour points, or a set of image contour points.
  • the multi-layer sampling of the image data and the depth data may be performed by extracting the plurality of sets of feature points utilizing two or more of a Difference of Gaussian (DoG) filter, a Laplacian of Gaussian (LoG) filter, a Canny filter, or a Sobel filter.
  • DoG Difference of Gaussian
  • LiG Laplacian of Gaussian
  • the plurality of sets of feature points may be extracted for each of a plurality of scaled representations corresponding to the one or more image frames.
  • the one or more processors may integrate the plurality of sets of feature points extracted for each of the plurality of scaled representations, and remove a subset of feature points from the integrated plurality of sets of feature points based on relative changes in depth data between the subset of feature points and respective neighboring feature points.
  • the set of sparse depth points may be generated further based on predetermined confidence scores associated with the set of sparse feature points, and each predetermined confidence score may indicate a likelihood the associated feature point corresponds to a determinative feature of the one or more image frames.
  • the one or more processors may send the image data to the external device, and the dense depth map corresponding to the one or more image frames may be reprojected by the external device based on the set of sparse depth points and the image data.
  • the controlling method of an electronic device includes the steps of obtaining image data and depth data corresponding to one or more image frames to be displayed on an external device which is associated with the electronic device and for providing extended reality (XR), determining a plurality of sets of feature points corresponding to the one or more image frames based on a multi-layer sampling of the image data and the depth data, generating a set of sparse feature points determined based on relative changes in depth data with respect to the plurality of sets of feature points based on an integration of the plurality of sets of feature points, generating a set of sparse depth points based on the set of sparse feature points and the depth data, and sending the set of sparse depth points to the external device for reconstruction of a dense depth map corresponding to the one or more image frames utilizing the set of sparse depth points.
  • XR extended reality
  • the plurality of sets of feature points may include two or more of a set of object feature points, a set of edge feature points, a set of object contour points, or a set of image contour points.
  • the multi-layer sampling of the image data and the depth data may be performed by extracting the plurality of sets of feature points utilizing two or more of a Difference of Gaussian (DoG) filter, a Laplacian of Gaussian (LoG) filter, a Canny filter, or a Sobel filter.
  • DoG Difference of Gaussian
  • LiG Laplacian of Gaussian
  • controlling method of an electronic device may further include the steps of integrating the plurality of sets of feature points extracted for each of the plurality of scaled representations, and removing a subset of feature points from the integrated plurality of sets of feature points based on relative changes in depth data between the subset of feature points and respective neighboring feature points.
  • the set of sparse depth points may be generated further based on predetermined confidence scores associated with the set of sparse feature points, and each predetermined confidence score may indicate a likelihood the associated feature point corresponds to a determinative feature of the one or more image frames.
  • controlling method of an electronic device may further include the step of sending the image data to the external device, and the dense depth map corresponding to the one or more image frames may be reprojected by the external device based on the set of sparse depth points and the image data.
  • FIG. 1 is a diagram illustrating an extended reality (XR) system according to an embodiment of this disclosure
  • FIG. 2 is a diagram illustrating respective workflow diagrams for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points, respectively;
  • FIG. 3 is a diagram illustrating an example diagram of multi-scale feature point extraction
  • FIGs. 4A, 4B, 4C, 4D, and 4E are diagrams illustrating respective example source image and running examples of techniques for generating a set of feature points, edges, object contours, and image contours;
  • FIG. 5A is a diagram illustrating a resulting example of integrating detected image features to a set of sparse depth points
  • FIG. 5B is a diagram illustrating example depth map results reconstructed from extracted sparse depth point sets
  • FIG. 6 is a diagram illustrating an example diagram for reconstructing a dense depth map based on a generated set of sparse depth points
  • FIG. 7 is a flow diagram of a method for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points;
  • FIG. 8 is a diagram illustrating an example computer system according to an embodiment of this disclosure.
  • the present embodiments are directed toward techniques for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points to reduce data throughput and compute load between an electronic device (it may also be referred to as a computing device) and an external device (it may also be referred to as an extended reality (XR) display device).
  • an electronic device it may also be referred to as a computing device
  • an external device it may also be referred to as an extended reality (XR) display device.
  • XR extended reality
  • an electronic device may obtain image data and depth data corresponding to one or more image frames to be displayed on an external device associated with the electronic device.
  • the electronic device may then determine a number of sets of feature points corresponding to the one or more image frames based on a multi-layer sampling of the image data and the depth data.
  • the number of sets of feature points may include two or more of a set of object feature points, a set of edge feature points, a set of object contour points, or a set of image contour points.
  • the electronic device may then determine a number of sets of feature points corresponding to the one or more image frames based on a multi-layer sampling of the image data and the depth data.
  • the multi-layer sampling of the image data and the depth data may be performed by extracting the number of sets of feature points utilizing two or more of a Difference of Gaussian (DoG) filter, a Laplacian of Gaussian (LoG) filter, a Canny filter, or a Sobel filter.
  • DoG Difference of Gaussian
  • LiG Laplacian of Gaussian
  • Canny filter a Canny filter
  • Sobel filter a Sobel filter
  • the electronic device may then generate a set of sparse feature points based on an integration of the number of sets of feature points, in which the set of sparse feature points may be determined based on relative changes in depth data with respect to the plurality of sets of feature points.
  • the electronic device may generate the set of sparse feature points by integrating the number of sets of feature points extracted for each of the plurality of scaled representations and removing a subset of feature points from the integrated number of sets of feature points based on relative changes in depth data between the subset of feature points and respective neighboring feature points.
  • the electronic device may then generate a set of sparse depth points based on the set of sparse feature points and the depth data.
  • the set of sparse depth points may be generated based on predetermined confidence scores associated with the set of sparse feature points, in which each predetermined confidence score may indicate a likelihood the associated feature point corresponds to a determinative feature of the one or more image frames.
  • the electronic device may then send the set of sparse depth points to the external device for reconstruction of the one or more image frames utilizing the set of sparse depth points.
  • the electronic device may send the set of sparse depth points along with the image data to the external device, which may then reconstruct the one or more image frames by combining the image data with the corresponding set of sparse depth points.
  • the electronic device may perform an adaptive process that extracts feature points from a depth map or one or more RGB-D image frames where depths suddenly change, such as object contours, object edges, and object features.
  • the electronic device may forgo extracting feature points where depths change only minimally (e.g., smoothly transition) or do not change at all, such as planes, cubes, and smooth surfaces of the depth map or one or more RGB-D image frames.
  • the electronic device may provide to the external device a depth map for reconstruction and re-projection, including only sparse depth points and sufficient object information to effectively and efficiently recover the depth information of the original depth map or one or more original RGB-D image frames generated by the electronic device.
  • the data throughput e.g., Wi-Fi data throughput
  • the data throughput may be reduced and load between the electronic device and the external device may be computed while maintaining desirable image quality with respect the reconstructed depth maps or RGB-D frames ultimately projected and/or re-projected onto the displays of the external device.
  • Extended reality used in the description of this disclosure may refer to a form of electronic-based reality that has been manipulated in some manner before presentation to a user, including, for example, virtual reality (VR), augmented reality (AR), mixed reality (MR), hybrid reality, simulated reality, immersive reality, holography, or any combination thereof.
  • extended reality content may include completely computer-generated content or partially computer-generated content combined with captured content (e.g., real-world images).
  • the "extended reality” content may also include video, audio, haptic feedback, or some combination thereof, any of which may be presented in a single channel or in multiple channels (such as stereo video that produces a three-dimensional (3D) effect to the viewer).
  • extended reality may be associated with applications, products, accessories, services, or a combination thereof, that, for example, may be utilized to create content in extended reality and/or utilized in (e.g., perform activities) in extended reality.
  • extended reality content may be implemented on various platforms, including a head-mounted device (HMD) connected to a host computer system, a standalone HMD, a mobile device or computing system, or any other hardware platform capable of providing extended reality content to one or more viewers.
  • HMD head-mounted device
  • a "current image frame" used in the description of this disclosure may refer to a most recent image frame or a most recent set of image frames that may be either sent (e.g., pushed) to an external device from a computing platform or requested or loaded (e.g., pulled) from the computing platform by the external device for image or depth processing and analysis.
  • the "current image frame” may simply correspond to the latest image frame (of an N set of RGB-D image frames being rendered by the computing platform) that may be pushed to, or pulled by, the external device. That is, all of the image frames of the N set of RGB-D image frames may not be provided from the computing platform to the external device, and thus the "current image frame” may simply refer to the most recent image that is indeed sent from the computing platform to the external device.
  • FIG. 1 is a diagram illustrating an example extended reality (XR) system 100 that may be suitable for selectively re-projecting depth maps based on image and depth data and pose data updates according to an embodiment of this disclosure.
  • XR extended reality
  • the XR system 100 may include an external device 102, a network 104, and an electronic device 106.
  • a user may wear the external device 102 that may display visual extended reality content to the user.
  • the external device 102 may include an audio device that may provide audio extended reality content to the user.
  • the external device 102 may include one or more cameras which can capture images and videos of environments.
  • the external device 102 may include an eye tracking system to determine the vergence distance of the user.
  • the external device 102 may include a lightweight head-mounted display (HMD) (e.g., goggles, eyeglasses, spectacles, a visor, and so forth).
  • HMD head-mounted display
  • the external device 102 may also include a non-HMD device, such as a lightweight handheld display device or one or more laser projecting spectacles (e.g., spectacles that may project a low-powered laser onto a user's retina to project and display image or depth content to the user).
  • the network 104 may include, for example, any of various wireless communications networks (e.g., WLAN, WAN, PAN, cellular, WMN, WiMAX, GAN, 6LowPAN, and so forth) that may be suitable for communicatively coupling the external device 102 to the electronic device 106.
  • the electronic device 106 may include, for example, a standalone host computing system, an on-board computer system integrated with the external device 102, a mobile device, or any other hardware platform that may be capable of providing extended reality content to the external device 102.
  • the electronic device 106 may include, for example, a cloud-based computing architecture (including one or more servers 108 and data stores 110) suitable for hosting and servicing XR applications or experiences executing on the external device 102.
  • a cloud-based computing architecture including one or more servers 108 and data stores 110
  • the electronicdevice 106 may include a Platform as a Service (PaaS) architecture, a Software as a Service (SaaS) architecture, and an Infrastructure as a Service (IaaS), or other similar cloud-based computing architecture.
  • PaaS Platform as a Service
  • SaaS Software as a Service
  • IaaS Infrastructure as a Service
  • the external device 102 may, due to the smaller architectural area, include reduced power management (e.g., batteries, battery size) and thermal management (e.g., cooling fans, heat sinks, and so forth) electronics.
  • reduced power management e.g., batteries, battery size
  • thermal management e.g., cooling fans, heat sinks, and so forth
  • FIG. 2 is a diagram illustrating a workflow diagram 200A and a workflow diagram 200B for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points.
  • the workflow diagram 200A may correspond to, and be performed, for example, by the electronic device 106 as discussed above with respect to FIG. 1.
  • the workflow diagram 200B may correspond to, and be performed, for example, by the external device 102 as discussed above with respect to FIG. 1.
  • the workflow diagram 200A may begin with the electronic device 106 accessing updated (R)ed, (G)reen, (B)lue, image data 202A and (D)epth data 204 with respect to, for example, one or more 2D, 2.5D, or 3D images to be provided to the external display device 102 for rendering to a user.
  • the workflow diagram 200A may then continue with the electronic device 106 performing an adaptive depth point extraction process 206.
  • the electronic device 106 may first perform object feature point extraction 208.
  • the electronic device 106 may perform object feature point extraction 208 at pixel locations at which pixel intensity values and depth values may suddenly change based on, for example, a multi-scale feature point extraction algorithm to extract the object feature points.
  • an initial layer sampling of the multi-layer sampling of the RGB image data 202A may be performed by extracting the object feature points utilizing, for example, a Difference of Gaussian (DoG) filter, a Laplacian of Gaussian (LoG) filter, or other similar filter that may be useful extracting object feature points from one or more of a number of scaled representations (e.g., Gaussian scale space representations) of the RGB image data 202A.
  • DoG Difference of Gaussian
  • LiG Laplacian of Gaussian
  • the electronic device 106 may then integrate the object feature points of all scaled representations and verify each object feature point with the corresponding depth data 204 (e.g., monochromatic depth map, RGB-D image frames). For example, in particular embodiments, the electronic device 106 may remove any object feature points at pixel locations at which the depth data 204 (e.g., monochromatic depth map, RGB-D image frames) change only minimally (e.g., smoothly transition) or do not change at all (e.g., along planes, cubes, smooth surfaces, and so forth) as compared to respective neighboring object feature points within the RGB image data 202A.
  • the depth data 204 e.g., monochromatic depth map, RGB-D image frames
  • the electronic device 106 may also generate one or more confidence scores (e.g., ranging from “0" to "100") or a confidence map, which may include, for example, an indication of a likelihood the associated object feature point corresponds to a determinative feature of objects within the within RGB image data 202A.
  • one or more confidence scores e.g., ranging from “0" to "100”
  • a confidence map which may include, for example, an indication of a likelihood the associated object feature point corresponds to a determinative feature of objects within the within RGB image data 202A.
  • the electronic device 106 may then perform object edge detection and extraction 210.
  • another layer sampling of the multi-layer sampling of the RGB image data 202A may be performed by extracting the object edge features utilizing, for example, a Canny filter, a Sobel filter, or other similar filter that may be useful extracting object edge features from one or more of the number of scaled representations (e.g., Gaussian scale space representations) of the RGB image data 202A to, for example, accurately capture the structure of objects of the RGB image data 202A.
  • scaled representations e.g., Gaussian scale space representations
  • the electronic device 106 may then integrate the object edge features of all scaled representations and verify each object edge feature with the corresponding depth data 204 (e.g., monochromatic depth map, RGB-D image frames).
  • depth data 204 e.g., monochromatic depth map, RGB-D image frames
  • the object edge features may represent object shape changes within the RGB image data 202A as corresponding to changes in depth.
  • the electronic device 106 may remove any object edge features at pixel locations at which the depth data 204 (e.g., monochromatic depth map, RGB-D image frames) change only minimally (e.g., smoothly transition) or do not change at all (e.g., along planes, cubes, smooth surfaces, and so forth) as compared to respective neighboring object edge features within RGB image data 202A.
  • the depth data 204 e.g., monochromatic depth map, RGB-D image frames
  • the electronic device 106 may also generate one or more confidence scores (e.g., ranging from “0" to "100") or a confidence map, which may include, for example, an indication of a likelihood the associated object edge feature corresponds to a determinative feature of objects within the RGB image data 202A.
  • one or more confidence scores e.g., ranging from “0" to "100”
  • a confidence map which may include, for example, an indication of a likelihood the associated object edge feature corresponds to a determinative feature of objects within the RGB image data 202A.
  • the electronic device 106 may then perform object contour detection and extraction 212 and image contour detection and extraction 214.
  • another layer sampling of the multi-layer sampling of the RGB image data 202A may be performed by extracting object contour features and image contour features (e.g., background pixels) that may be utilized, for example, to supplement the object feature points and object edge features.
  • object contour features and image contour features e.g., background pixels
  • reconstructed image frames may lose RGB image data 202A and depth data 204 (e.g., monochromatic depth map, RGB-D image frames) information, such as smoothed out features and/or feature points missing from certain object contour locations.
  • the electronic device 106 may also generate one or more confidence scores (e.g., ranging from “0" to "100") or a confidence map, which may include, for example, an indication of a likelihood the associated object contours and image contours correspond to determinative features of objects within the RGB image data 202A.
  • one or more confidence scores e.g., ranging from "0" to "100”
  • a confidence map which may include, for example, an indication of a likelihood the associated object contours and image contours correspond to determinative features of objects within the RGB image data 202A.
  • the electronic device 106 may then integrate the extracted and verified number of feature points, the extracted and verified number of edge features, and the extracted and verified number of object and image contour features to generate a set of sparse feature points.
  • the electronic device 106 may first perform object contour labeling 216, which may be utilized, for example, classify certain objects or features for applications, such as object recognition, occlusion, 3D analysis, and so forth.
  • the electronic device 106 may then perform an integration 218 of the extracted and verified number of feature points, the extracted and verified number. For example, in particular embodiments, the electronic device 106 may integrate the feature points generated from the feature detection and extraction 208, the edge detection and extraction 210, the object contour detection and extraction 212, and the image contour detection and extraction 214 together to generate a granular and set of sparse feature points.
  • the electronic device 106 may perform one or more additional verifications to determine and filter out duplicated feature points and/or feature points that are positioned too closely together for each to be individually resolvable.
  • the electronic device 106 may then perform an integration 220 of the generated set of sparse feature points with the corresponding depth data 204 (e.g., monochromatic depth map, RGB-D image frames). In particular embodiments, the electronic device 106 may then perform one or more additional verifications to remove any of the sparse set of feature points at pixel locations at which the depth data 204 (e.g., monochromatic depth map, RGB-D image frames) change only minimally (e.g., smoothly transition) or do not change at all as compared to respective neighboring sparse feature points within the RGB image data 202A.
  • the depth data 204 e.g., monochromatic depth map, RGB-D image frames
  • the electronic device 106 may then generate a granular and set of sparse depth points 222. In particular embodiments, the electronic device 106 may then divide the set of sparse depth points into, for example, two or more levels of sparse depth points based on the respective confidence scores or confidence maps predetermined with respect to the object feature point extraction 208, the object edge detection and extraction 210, and the object contour detection and extraction 212 and image contour detection and extraction 214 discussed above.
  • the electronic device 106 may then transmit the set of sparse depth points 224 to the external device 102 over the network 104. For example, in particular embodiments, by generating the two or more levels of sparse depth points divided according to the respective confidence scores or confidence maps, the electronic device 106 may control and reduce, for example, the number of depth points that is transmitted to the external device 102 at any point in time without compromising the quality of the depth map reconstruction and re-projection performed by the external device 102.
  • the network 104 bandwidth and/or throughput conditions when the network 104 bandwidth and/or throughput conditions are suitable for large data transmissions, larger sets of sparse depth points may be transmitted to the external device 102, and, in contrast, when the network 104 bandwidth and/or throughput conditions are unsuitable for large data transmissions, reduced-sized sets of sparse depth points may be transmitted to the external device 102.
  • the external device 102 may receive the set of sparse depth points 224 from the electronic device 106.
  • the external device 102 may also receive the RGB image data 202B (e.g., one or more current RGB image frames) from the electronic device 106.
  • the external device 102 may then perform dense depth map reconstruction 226 based on the set of sparse depth points 224 received from the electronic device 106.
  • the external device 102 may then compute one or more depth differences between pixel locations r and one or more respective neighboring pixel locations s (e.g., a weighted average of the neighboring pixel locations s) within the RGB image data 202B.
  • the external device 102 may compute the one or more depth differences as expressed below:
  • the external device 102 may then minimize the one or more depth differences 230 to determine the depth at one or more particular pixel locations r and may iteratively perform the minimizing of the one or more depth differences 230 until the depth at each pixel location r is determined.
  • XR display device 102 may define a window with its respective neighboring pixel location s and generate an objective function of depth difference.
  • the external device 102 may then minimize the objective function to obtain depth at each pixel location r.
  • the external device 102 may minimize the one or more depth differences 230 to determine the depth at one or more particular pixel locations r as expressed by:
  • the external device 102 may then reconstruct a dense depth map 232, which may include, for example, a reconstruction or partial reconstruction of the original depth data 204.
  • the external device 102 may then perform one or more re-projections 234 of RGB-D image frames onto the displays of the external device 102.
  • the electronic device 106 may perform an adaptive process that extracts feature points from the RGB image data 202A and depth data 204 (e.g., grayscale depth image frames) at pixel locations at which depths suddenly change, such as object contours, object edges, and object features.
  • feature points from the RGB image data 202A and depth data 204 (e.g., grayscale depth image frames) at pixel locations at which depths suddenly change, such as object contours, object edges, and object features.
  • the electronic device 106 may forgo extracting feature points, edge points, contour points, and so forth where depths change only minimally (e.g., smoothly transition) or do not change at all, such as planes, cubes, and smooth surfaces of the RGB image data 202A and depth data 204.
  • the electronic device 106 may provide to the external device 102 a depth map for reconstruction and re-projection, including only sparse depth points and sufficient object information to effectively and efficiently recover the depth information of the original RGB image data 202A and depth data 204 (e.g., grayscale depth image frames) generated by the electronic device 106.
  • the presently disclosed embodiments may thus reduce the data throughput (e.g., Wi-Fi data throughput) and compute load between the electronic device 106 and the external device 102 while maintaining desirable image quality with respect the reconstructed image data 202A and depth data 204 (e.g., grayscale depth image frames) ultimately projected and/or re-projected onto the displays of the external device 102.
  • FIG. 3 is a diagram illustrating an example diagram 300 of the detection of the feature points of the RGB image data 202A as discussed above with respect to FIG. 2.
  • the RGB image data 202 may be scaled to a number of scaled representations 304, 306, and 308 (e.g., Gaussian scale space representations).
  • each of the number of scaled representations 304, 306, and 308 (e.g., Gaussian scale space representations) may represent, for example, the RGB image data 202A as a series of differently blurred images scaled from least blurred (scaled representation 304) to greatest blurred (e.g., scaled representation 308).
  • the number of scaled representations 304, 306, and 308 may be then integrated by a combiner 310 (e.g., summed together) and utilized to generate an integrated set 312 of the feature points of the RGB image data 202A.
  • a combiner 310 e.g., summed together
  • the example diagram 300 represents only one embodiment of the detection and extraction of the feature points of the RGB image data 202A.
  • the process as illustrated by the example diagram 300 may be performed individually for each of the detection and extraction of the feature points, edge features, and object and image contour features of the RGB image data 202A.
  • FIGs. 4A, 4B, 4C, 4D, and 4E are diagrams illustrating respective running examples of the techniques for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points, as discussed above with respect to FIG. 2.
  • FIG. 4A illustrates an original RGB-D image 400A that may be generated by the electronic device 106 and to be displayed by the external device 102.
  • FIG. 4B illustrates an example result 400B of the detection, extraction, integration, and depth verification of the feature points as discussed above with respect to FIG. 2, with the feature points being color-coded respect to confidence score.
  • FIG. 4B illustrates an example result 400B of the detection, extraction, integration, and depth verification of the feature points as discussed above with respect to FIG. 2, with the feature points being color-coded respect to confidence score.
  • FIG. 4C illustrates an example result 400C of the detection, extraction, integration, and depth verification of the edge features as discussed above with respect to FIG. 2.
  • FIG. 4D illustrates an example result 400D of the detection, extraction, and depth verification of the object contour features
  • FIG. 4E illustrates an example result 400E of the detection, extraction, integration, and depth verification of the image contour features, as each discussed above with respect to FIG. 2.
  • FIG. 5A is a diagram illustrating a resulting example 500A of integrating a set of sparse depth points selected from original depth map 204 corresponding to extracted feature points, edge features, contour features illustrated in FIGs. 4A, 4B, 4C, 4D, and 4E according to an embodiment of this disclosure.
  • the example 500 may represent a reconstruction of the original RGB-D image 400A of FIG. 4A reconstructed based on, for example, a set of sparse depth points determined based on an integrated set of sparse feature points derived from the detected, extracted, integrated, and depth verified feature points (e.g., as illustrated by FIG. 4B), edge features (e.g., as illustrated by FIG. 4C), and object contour and image contour features (as illustrated by FIG. 4D and FIG. 4E, respectively).
  • a set of sparse depth points determined based on an integrated set of sparse feature points derived from the detected, extracted, integrated, and depth verified feature points (e.g., as illustrated by FIG. 4B), edge features (e.g., as illustrated by FIG. 4C), and object contour and image contour features (as illustrated by FIG. 4D and FIG. 4E, respectively).
  • FIG. 5B is a diagram illustrating example depth map results reconstructed from extracted sparse depth point sets according to an embodiment of this disclosure.
  • example 502 and example 504 show depth map reconstructed from 16494 depth points and 1823 depth points, respectively.
  • the electronic device 106 may provide to the external device 102 a depth map for reconstruction and re-projection, including only a set of sparse depth points and sufficient object information to effectively and efficiently recover the depth information of the original RGB image data 202A and depth data 204 (e.g., grayscale depth image frames) generated by the electronic device 106.
  • the data throughput e.g., Wi-Fi data throughput
  • compute load between the electronic device 106 and the external device 102 may be reduced while maintaining desirable image quality with respect to the reconstructed image data 202A and depth data 204 (e.g., grayscale depth image frames) ultimately projected and/or re-projected onto the displays of the external device 102.
  • the reconstructed image data 202A and depth data 204 e.g., grayscale depth image frames
  • FIG. 6 is a diagram illustrating an example diagram 600 of the reconstruction of a dense depth map based on, for example, the set of sparse depth points received from the electronic device 106, as generally discussed above with respect to the workflow diagram 200B of FIG. 2.
  • the external device 102 may compute one or more depth differences between, for example, pixel locations 604 (e.g., pixel locations r) and one or more respective neighboring pixel locations 606 and 608 (neighboring pixels s) within the RGB pixel grid 602.
  • pixel locations 604 e.g., pixel locations r
  • neighboring pixel locations 606 and 608 neighbored pixels s
  • the external device 102 may then minimize the one or more depth differences to determine the depth at one or more particular pixel locations 604 (e.g., pixel locations r) and may iteratively perform the minimizing of the one or more depth differences until the depth at each pixel location 604 (e.g., pixel locations r) is determined.
  • the external device 102 may define a window with its respective neighboring pixel location 606, 608 (e.g., neighboring pixel location s) and generate an objective function of depth difference.
  • the external device 102 may then minimize the objective function to obtain depth at each pixel location 604 (e.g., pixel location r).
  • the missing pixel locations 610 may represent pixel locations for which depth is undetermined, and thus the aforementioned depth difference and minimization techniques may be iteratively performed to determine depth for each of the missing pixel locations 610.
  • the external device 102 may then reconstruct a dense depth map and re-project one or more RGB-D image frames.
  • FIG. 7 is a flow diagram of a method 700 for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points according to an embodiment of this disclosure.
  • the method 700 may be performed utilizing one or more processing devices (e.g., electronic device 106) that may include hardware (e.g., a general purpose processor, a graphic processing unit (GPU), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor (AP), a visual processing unit (VPU), a neural processing unit (NPU), a neural decision processor (NDP), or any other processing device(s) that may be suitable for processing image data), software (e.g., instructions running/executing on one or more processors), firmware (e.g., microcode), or some combination thereof.
  • hardware e.g., a general purpose processor, a graphic processing unit (GPU), an application-specific integrated circuit (ASIC), a system-on-chip (SoC), a microcontroller, a field-programmable gate array (FPGA), a central processing unit (CPU), an application processor
  • the method 700 may begin block 702 with the one or more processing devices (e.g., electronic device 106) accessing and obtaining image data and depth data corresponding to one or more image frames to be displayed on an extended reality (XR) display device (e.g., external device 102) associated with the electronic device.
  • the one or more processing devices e.g., electronic device 106
  • XR extended reality
  • the method 700 may then continue at block 704 with the one or more processing devices (e.g., electronic device 106) determining a plurality of sets of feature points corresponding to the one or more image frames based on a multi-layer sampling of the image data and the depth data.
  • the one or more processing devices e.g., electronic device 106
  • the method 700 may then continue at block 706 with the one or more processing devices (e.g., electronic device 106) generating a set of sparse feature points based on an integration of the plurality of sets of feature points, in which the set of sparse feature points are determined based on relative changes in depth data with respect to the plurality of sets of feature points.
  • the one or more processing devices e.g., electronic device 106
  • the method 700 may then continue at block 708 with the one or more processing devices (e.g., electronic device 106) generating a set of sparse depth points based on the set of sparse feature points and the depth data.
  • the one or more processing devices e.g., electronic device 106
  • the method 700 may then conclude at block 710 with the one or more processing devices (e.g., electronic device 106) sending the set of sparse depth points to the external device for reconstruction of the one or more image frames utilizing the set of sparse depth points.
  • the one or more processing devices e.g., electronic device 106
  • the electronic device 106 may perform an adaptive process that extracts feature points from the RGB image data 202A and depth data 204 (e.g., RGB-D image frames) at pixel locations at which depths suddenly change, such as object contours, object edges, and object features.
  • RGB image data 202A and depth data 204 e.g., RGB-D image frames
  • the electronic device 106 may forgo extracting feature points, edge points, contour points, and so forth where depths change only minimally (e.g., smoothly transition) or do not change at all, such as planes, cubes, and smooth surfaces of the RGB image data 202A and depth data 204.
  • the electronic device 106 may provide to the external device 102 a depth map for reconstruction and re-projection, including only sparse depth points and sufficient object information to effectively and efficiently recover the depth information of the original RGB image data 202A and depth data 204 (e.g., RGB-D image frames) generated by the electronic device 106.
  • the data throughput e.g., Wi-Fi data throughput
  • compute load between the electronic device 106 and the external device 102 may be reduced while maintaining desirable image quality with respect to the reconstructed image data 202A and depth data 204 (e.g., RGB-D image frames) ultimately projected and/or re-projected onto the displays of the external device 102.
  • FIG. 8 is a diagram illustrating an example computer system 800 that may be utilized for generating a set of sparse depth points and reconstructing a dense depth map based on the generated sparse depth points according to an embodiment of this disclosure.
  • one or more computer systems 800 perform one or more steps of one or more methods described or illustrated herein.
  • one or more computer systems 800 provide functionality described or illustrated herein.
  • software running on one or more computer systems 800 performs one or more steps of one or more methods described or illustrated herein or provides functionality described or illustrated herein.
  • Particular embodiments include one or more portions of one or more computer systems 800.
  • a computer system may encompass electronic device 106, and vice versa.
  • a computer system may encompass one or more computer systems.
  • computer system 800 may be an embedded computer system, a system-on-chip (SOC), a single-board computer system (SBC) (e.g., a computer-on-module (COM) or system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a mesh of computer systems, a mobile telephone, a personal digital assistant (PDA), a server, a tablet computer system, an augmented/virtual reality device, or a combination of two or more of these.
  • SBC single-board computer system
  • PDA personal digital assistant
  • server a server
  • tablet computer system augmented/virtual reality device
  • one or more computer systems 800 may perform without substantial spatial or temporal limitation one or more steps of one or more methods described or illustrated herein.
  • one or more computer systems 800 may perform in real time or in batch mode one or more steps of one or more methods described or illustrated herein.
  • One or more computer systems 800 may perform at different times or at different locations one or more steps of one or more methods described or illustrated herein, where appropriate.
  • computer system 800 or electronic device 106 included in the computer system includes a processor 802, memory 804, storage 806, an input/output (I/O) interface 808, a communication interface 810, and a bus 812.
  • processor 802 memory 804, storage 806, an input/output (I/O) interface 808, a communication interface 810, and a bus 812.
  • I/O input/output
  • this disclosure describes and illustrates a particular computer system having a particular number of particular components in a particular arrangement, this disclosure contemplates any suitable computer system having any suitable number of any suitable components in any suitable arrangement.
  • processor 802 includes hardware for executing instructions, such as those making up a computer program.
  • processor 802 may retrieve (or fetch) the instructions from an internal register, an internal cache, memory 804, or storage 806; decode and execute them; and then write one or more results to an internal register, an internal cache, memory 804, or storage 806.
  • processor 802 may include one or more internal caches for data, instructions, or addresses. This disclosure contemplates processor 802 including any suitable number of any suitable internal caches, where appropriate.
  • processor 802 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). Instructions in the instruction caches may be copies of instructions in memory 804 or storage 806, and the instruction caches may speed up retrieval of those instructions by processor 802.
  • TLBs translation lookaside buffers
  • Data in the data caches may be copies of data in memory 804 or storage 806 for instructions executing at processor 802 to operate on; the results of previous instructions executed at processor 802 for access by subsequent instructions executing at processor 802 or for writing to memory 804 or storage 806; or other suitable data.
  • the data caches may speed up read or write operations by processor 802.
  • the TLBs may speed up virtual-address translation for processor 802.
  • processor 802 may include one or more internal registers for data, instructions, or addresses. This disclosure contemplates processor 802 including any suitable number of any suitable internal registers, where appropriate.
  • processor 802 may include one or more arithmetic logic units (ALUs); be a multi-core processor; or include one or more processors 802.
  • memory 804 includes main memory for storing instructions for processor 802 to execute or data for processor 802 to operate on.
  • computer system 800 may load instructions from storage 806 or another source (such as, for example, another computer system 800) to memory 804.
  • Processor 802 may then load the instructions from memory 804 to an internal register or internal cache.
  • processor 802 may retrieve the instructions from the internal register or internal cache and decode them.
  • processor 802 may write one or more results (which may be intermediate or final results) to the internal register or internal cache.
  • Processor 802 may then write one or more of those results to memory 804.
  • processor 802 executes only instructions in one or more internal registers or internal caches or in memory 804 (as opposed to storage 806 or elsewhere) and operates only on data in one or more internal registers or internal caches or in memory 804 (as opposed to storage 806 or elsewhere).
  • One or more memory buses may couple processor 802 to memory 804.
  • Bus 812 may include one or more memory buses, as described below.
  • one or more memory management units reside between processor 802 and memory 804 and facilitate accesses to memory 804 requested by processor 802.
  • memory 804 includes random access memory (RAM).
  • This RAM may be volatile memory, where appropriate. Where appropriate, this RAM may be dynamic RAM (DRAM) or static RAM (SRAM). Moreover, where appropriate, this RAM may be single-ported or multi-ported RAM.
  • Memory 804 may include one or more memories 804, where appropriate.
  • storage 806 includes mass storage for data or instructions.
  • storage 806 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a Universal Serial Bus (USB) drive or a combination of two or more of these.
  • Storage 806 may include removable or non-removable (or fixed) media, where appropriate.
  • Storage 806 may be internal or external to computer system 800, where appropriate.
  • storage 806 is non-volatile, solid-state memory.
  • storage 806 includes read-only memory (ROM).
  • this ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EAROM), or flash memory or a combination of two or more of these.
  • This disclosure contemplates mass storage 806 taking any suitable physical form.
  • Storage 806 may include one or more storage control units facilitating communication between processor 802 and storage 806, where appropriate. Where appropriate, storage 806 may include one or more storages 806. Although this disclosure describes and illustrates particular storage, this disclosure contemplates any suitable storage.
  • I/O interface 808 includes hardware, software, or both, providing one or more interfaces for communication between computer system 800 and one or more I/O devices.
  • Computer system 800 may include one or more of these I/O devices, where appropriate.
  • One or more of these I/O devices may enable communication between a person and computer system 800.
  • an I/O device may include a keyboard, keypad, microphone, monitor, mouse, printer, scanner, speaker, still camera, stylus, tablet, touch screen, trackball, video camera, another suitable I/O device or a combination of two or more of these.
  • An I/O device may include one or more sensors. This disclosure contemplates any suitable I/O devices and any suitable I/O interfaces 806 for them.
  • I/O interface 808 may include one or more device or software drivers enabling processor 802 to drive one or more of these I/O devices.
  • I/O interface 808 may include one or more I/O interfaces 806, where appropriate.
  • communication interface 810 includes hardware, software, or both providing one or more interfaces for communication (such as, for example, packet-based communication) between computer system 800 and one or more other computer systems 800 or one or more networks.
  • communication interface 810 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire-based network or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network, such as a WI-FI network.
  • NIC network interface controller
  • WNIC wireless NIC
  • WI-FI network wireless network
  • computer system 800 may communicate with an ad hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or one or more portions of the Internet or a combination of two or more of these.
  • PAN personal area network
  • LAN local area network
  • WAN wide area network
  • MAN metropolitan area network
  • computer system 800 may communicate with a wireless PAN (WPAN) (such as, for example, a BLUETOOTH WPAN), a WI-FI network, a WI-MAX network, a cellular telephone network (such as, for example, a Global System for Mobile Communications (GSM) network), or other suitable wireless network or a combination of two or more of these.
  • Computer system 800 may include any suitable communication interface 810 for any of these networks, where appropriate.
  • Communication interface 810 may include one or more communication interfaces 810, where appropriate.
  • bus 812 includes hardware, software, or both coupling components of computer system 800 to each other.
  • bus 812 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a front-side bus (FSB), a HYPERTRANSPORT (HT) interconnect, an Industry Standard Architecture (ISA) bus, an INFINIBAND interconnect, a low-pin-count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a serial advanced technology attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or a combination of two or more of these.
  • Bus 812 may include one or more buses 812, where appropriate.
  • a computer-readable non-transitory storage medium or media may include one or more semiconductor-based or other integrated circuits (ICs) (such, as for example, field-programmable gate arrays (FPGAs) or application-specific ICs (ASICs)), hard disk drives (HDDs), hybrid hard drives (HHDs), optical discs, optical disc drives (ODDs), magneto-optical discs, magneto-optical drives, floppy diskettes, floppy disk drives (FDDs), magnetic tapes, solid-state drives (SSDs), RAM-drives, SECURE DIGITAL cards or drives, any other suitable computer-readable non-transitory storage media, or any suitable combination of two or more of these, where appropriate.
  • ICs such, as for example, field-programmable gate arrays (FPGAs) or application-specific ICs (ASICs)
  • HDDs hard disk drives
  • HHDs hybrid hard drives
  • ODDs optical disc drives
  • magneto-optical discs magneto-optical drives
  • a storage medium that is readable by machines may be provided in the form of a non-transitory storage medium.
  • the term 'non-transitory' only means that the device is a tangible device, and does not include a signal (e.g.: an electronic wave), and the term does not distinguish a case wherein data is stored semi-permanently in a storage medium and a case wherein data is stored temporarily.
  • 'a non-transitory storage medium' may include a buffer wherein data is temporarily stored.
  • a computer program product refers to a product, and it can be traded between a seller and a buyer.
  • a computer program product can be distributed in the form of a storage medium that is readable by machines (e.g.: a compact disc read only memory (CD-ROM)), or may be distributed directly between two user devices (e.g.: smartphones), and distributed on-line (e.g.: download or upload) through an application store (e.g.: Play StoreTM).
  • machines e.g.: a compact disc read only memory (CD-ROM)
  • CD-ROM compact disc read only memory
  • smartphones e.g.: smartphones
  • an application store e.g.: Play StoreTM
  • At least a portion of a computer program product may be stored in a storage medium such as the server of the manufacturer, the server of the application store, and the memory of the relay server at least temporarily, or may be generated temporarily.
  • references in the appended claims to an apparatus or system or a component of an apparatus or system being adapted to, arranged to, capable of, configured to, enabled to, operable to, or operative to perform a particular function encompasses that apparatus, system, component, whether or not it or that particular function is activated, turned on, or unlocked, as long as that apparatus, system, or component is so adapted, arranged, capable, configured, enabled, operable, or operative. Additionally, although this disclosure describes or illustrates particular embodiments as providing particular advantages, particular embodiments may provide none, some, or all of these advantages.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

Procédé consistant à accéder à des données d'image et à des données de profondeur correspondant à des trames d'image à afficher sur un dispositif d'affichage à réalité étendue (XR), et à déterminer des ensembles de points caractéristiques correspondant aux trames d'image sur la base d'un échantillonnage multicouche des données d'image et des données de profondeur. Le procédé consiste en outre à générer un ensemble de points caractéristiques clairsemés sur la base d'une intégration des ensembles de points caractéristiques. L'ensemble de points caractéristiques clairsemés est déterminé sur la base de changements relatifs de données de profondeur par rapport aux ensembles de points caractéristiques. Le procédé consiste en outre à générer un ensemble de points de profondeur clairsemés sur la base de l'ensemble de points caractéristiques clairsemés et des données de profondeur et à envoyer l'ensemble de points de profondeur clairsemés au dispositif externe en vue de la reconstruction d'une carte de profondeur dense correspondant aux trames d'image à l'aide de l'ensemble de points de profondeur clairsemés.
PCT/KR2021/013997 2021-03-11 2021-10-12 Dispositif électronique et procédé de commande de dispositif électronique WO2022191373A1 (fr)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US17/198,997 US11688073B2 (en) 2020-04-14 2021-03-11 Method and system for depth map reconstruction
US17/198,997 2021-03-11
KR1020210074887A KR20220127718A (ko) 2020-04-14 2021-06-09 전자 장치 및 전자 장치의 제어 방법
KR10-2021-0074887 2021-06-09

Publications (1)

Publication Number Publication Date
WO2022191373A1 true WO2022191373A1 (fr) 2022-09-15

Family

ID=83227915

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2021/013997 WO2022191373A1 (fr) 2021-03-11 2021-10-12 Dispositif électronique et procédé de commande de dispositif électronique

Country Status (1)

Country Link
WO (1) WO2022191373A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070024614A1 (en) * 2005-07-26 2007-02-01 Tam Wa J Generating a depth map from a two-dimensional source image for stereoscopic and multiview imaging
US20120134597A1 (en) * 2010-11-26 2012-05-31 Microsoft Corporation Reconstruction of sparse data
KR20140007367A (ko) * 2011-01-31 2014-01-17 마이크로소프트 코포레이션 삼차원 환경 재구성
US20190228504A1 (en) * 2018-01-24 2019-07-25 GM Global Technology Operations LLC Method and system for generating a range image using sparse depth data
EP3699736A1 (fr) * 2014-06-14 2020-08-26 Magic Leap, Inc. Procédés et systèmes de création d'une réalité virtuelle et d'une réalité augmentée

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070024614A1 (en) * 2005-07-26 2007-02-01 Tam Wa J Generating a depth map from a two-dimensional source image for stereoscopic and multiview imaging
US20120134597A1 (en) * 2010-11-26 2012-05-31 Microsoft Corporation Reconstruction of sparse data
KR20140007367A (ko) * 2011-01-31 2014-01-17 마이크로소프트 코포레이션 삼차원 환경 재구성
EP3699736A1 (fr) * 2014-06-14 2020-08-26 Magic Leap, Inc. Procédés et systèmes de création d'une réalité virtuelle et d'une réalité augmentée
US20190228504A1 (en) * 2018-01-24 2019-07-25 GM Global Technology Operations LLC Method and system for generating a range image using sparse depth data

Similar Documents

Publication Publication Date Title
US11719933B2 (en) Hand-locked rendering of virtual objects in artificial reality
US20230039100A1 (en) Multi-layer reprojection techniques for augmented reality
JP6946566B2 (ja) 静的な映像認識
US11625862B2 (en) Mirror reconstruction
CN112912823A (zh) 生成和修改增强现实或虚拟现实场景中对象的表示
US11288543B1 (en) Systems and methods for depth refinement using machine learning
US11688073B2 (en) Method and system for depth map reconstruction
US11734808B2 (en) Generating a composite image
US11182647B2 (en) Distributed sensor module for tracking
WO2022191373A1 (fr) Dispositif électronique et procédé de commande de dispositif électronique
US11615594B2 (en) Systems and methods for reconstruction of dense depth maps
US11715272B2 (en) 3D reconstruction of a moving object
US20210312713A1 (en) Object identification utilizing paired electronic devices
WO2021172950A1 (fr) Dispositif électronique et procédé pour reprojection de carte de profondeur sur un dispositif électronique
WO2022158890A1 (fr) Systèmes et procédés de reconstruction de cartes de profondeur dense
JP2002042158A (ja) 画像合成装置および画像合成方法およびプログラムを記録した媒体
WO2023146372A1 (fr) Reconstruction d'une scène tridimensionnelle
WO2021201638A1 (fr) Dispositif électronique et procédé d'identification d'objet utilisant un dispositif électronique apparié
US11321838B2 (en) Distributed sensor module for eye-tracking
US20230136662A1 (en) Parallax Asynchronous Spacewarp for Multiple Frame Extrapolation
US20220201271A1 (en) Temporal foveated rendering
CN113117341B (zh) 图片处理方法及装置、计算机可读存储介质、电子设备
WO2024043549A1 (fr) Procédé, appareil et support lisible par ordinateur pour générer un point clé facial d'un utilisateur dans une vidéo pour générer une vidéo synthétique
US20240119672A1 (en) Systems, methods, and media for generating visualization of physical environment in artificial reality
EP4233011A1 (fr) Tramage corrigé par distorsion

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21930473

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21930473

Country of ref document: EP

Kind code of ref document: A1