JP7241775B2 - 深度推定システムの自己教師ありトレーニング - Google Patents

深度推定システムの自己教師ありトレーニング Download PDF

Info

Publication number
JP7241775B2
JP7241775B2 JP2020564565A JP2020564565A JP7241775B2 JP 7241775 B2 JP7241775 B2 JP 7241775B2 JP 2020564565 A JP2020564565 A JP 2020564565A JP 2020564565 A JP2020564565 A JP 2020564565A JP 7241775 B2 JP7241775 B2 JP 7241775B2
Authority
JP
Japan
Prior art keywords
image
depth
difference
images
frame
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
JP2020564565A
Other languages
English (en)
Japanese (ja)
Other versions
JP2021526680A5 (https=
JP2021526680A (ja
JPWO2019222467A5 (https=
Inventor
クレマン ゴダール
アオダ オイシン マック
ガブリエル ジェイ ブロストウ
マイケル ファーマン
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Niantic Inc
Original Assignee
Niantic Inc
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
Application filed by Niantic Inc filed Critical Niantic Inc
Publication of JP2021526680A publication Critical patent/JP2021526680A/ja
Publication of JP2021526680A5 publication Critical patent/JP2021526680A5/ja
Publication of JPWO2019222467A5 publication Critical patent/JPWO2019222467A5/ja
Application granted granted Critical
Publication of JP7241775B2 publication Critical patent/JP7241775B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/20—Image signal generators
    • H04N13/271—Image signal generators wherein the generated image signals comprise depth maps or disparity maps
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/579—Depth or shape recovery from multiple images from motion
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • G06T7/593—Depth or shape recovery from multiple images from stereo images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/97—Determining parameters from multiple pictures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30244—Camera pose
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/20—Image signal generators
    • H04N13/204—Image signal generators using stereoscopic image cameras
    • H04N13/239—Image signal generators using stereoscopic image cameras using two two-dimensional [2D] image sensors having a relative position equal to or related to the interocular distance
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N2013/0074—Stereoscopic image analysis
    • H04N2013/0081—Depth or disparity estimation from stereoscopic image signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N2013/0074—Stereoscopic image analysis
    • H04N2013/0088—Synthesising a monoscopic image signal from stereoscopic images, e.g. synthesising a panoramic or high resolution monoscopic image

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Processing Or Creating Images (AREA)
  • Image Analysis (AREA)
  • User Interface Of Digital Computer (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Eye Examination Apparatus (AREA)
  • Image Processing (AREA)
JP2020564565A 2018-05-17 2019-05-16 深度推定システムの自己教師ありトレーニング Active JP7241775B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201862673045P 2018-05-17 2018-05-17
US62/673,045 2018-05-17
PCT/US2019/032616 WO2019222467A1 (en) 2018-05-17 2019-05-16 Self-supervised training of a depth estimation system

Publications (4)

Publication Number Publication Date
JP2021526680A JP2021526680A (ja) 2021-10-07
JP2021526680A5 JP2021526680A5 (https=) 2022-04-22
JPWO2019222467A5 JPWO2019222467A5 (https=) 2022-04-22
JP7241775B2 true JP7241775B2 (ja) 2023-03-17

Family

ID=68533243

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2020564565A Active JP7241775B2 (ja) 2018-05-17 2019-05-16 深度推定システムの自己教師ありトレーニング

Country Status (9)

Country Link
US (3) US11082681B2 (https=)
EP (1) EP3794555B1 (https=)
JP (1) JP7241775B2 (https=)
KR (1) KR102506959B1 (https=)
CN (1) CN112534475B (https=)
AU (1) AU2019270095B9 (https=)
CA (1) CA3100640C (https=)
TW (1) TWI790380B (https=)
WO (1) WO2019222467A1 (https=)

Families Citing this family (74)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019222467A1 (en) * 2018-05-17 2019-11-21 Niantic, Inc. Self-supervised training of a depth estimation system
JP2020042665A (ja) * 2018-09-12 2020-03-19 キヤノン株式会社 情報処理装置、情報処理装置の制御方法及びプログラム
US20200137380A1 (en) * 2018-10-31 2020-04-30 Intel Corporation Multi-plane display image synthesis mechanism
US11995854B2 (en) * 2018-12-19 2024-05-28 Nvidia Corporation Mesh reconstruction using data-driven priors
US11138751B2 (en) * 2019-07-06 2021-10-05 Toyota Research Institute, Inc. Systems and methods for semi-supervised training using reprojected distance loss
US10762650B1 (en) * 2019-09-13 2020-09-01 Toyota Motor Engineering & Manufacturing North America, Inc. System and method for estimating depth using a monocular camera
US11210802B2 (en) * 2019-09-24 2021-12-28 Toyota Research Institute, Inc. Systems and methods for conditioning training data to avoid learned aberrations
US11294996B2 (en) 2019-10-15 2022-04-05 Assa Abloy Ab Systems and methods for using machine learning for image-based spoof detection
US11348375B2 (en) * 2019-10-15 2022-05-31 Assa Abloy Ab Systems and methods for using focal stacks for image-based spoof detection
EP3822913B1 (en) * 2019-11-14 2024-09-25 Continental Autonomous Mobility Germany GmbH Spatial aware object detection by flash lidar and camera fusion based super-resolution
CN111179326B (zh) * 2019-12-27 2020-12-29 精英数智科技股份有限公司 一种单目深度估计方法、系统、设备及存储介质
WO2021150016A1 (en) 2020-01-20 2021-07-29 Samsung Electronics Co., Ltd. Methods and systems for performing tasks on media using attribute specific joint learning
WO2021154099A1 (en) * 2020-01-30 2021-08-05 Weta Digital Limited System for image compositing including training with synthetic data
US11710247B2 (en) 2020-01-30 2023-07-25 Unity Technologies Sf System for image compositing including training with synthetic data
US11503266B2 (en) 2020-03-06 2022-11-15 Samsung Electronics Co., Ltd. Super-resolution depth map generation for multi-camera or other environments
US11741675B2 (en) * 2020-03-10 2023-08-29 Niantic, Inc. Determining traversable space from single images
CN113572919B (zh) * 2020-04-29 2023-06-30 思特威(上海)电子科技股份有限公司 快速自动曝光调节方法及双目系统
CN113592875B (zh) * 2020-04-30 2024-01-23 阿里巴巴集团控股有限公司 数据处理方法、图像处理方法、存储介质及计算设备
US11341719B2 (en) * 2020-05-07 2022-05-24 Toyota Research Institute, Inc. System and method for estimating depth uncertainty for self-supervised 3D reconstruction
TWI772806B (zh) * 2020-05-22 2022-08-01 國立陽明交通大學 場景理解系統及方法
TW202230287A (zh) * 2020-06-01 2022-08-01 美商高通公司 用於遮擋處理技術的方法和裝置
CN111709890B (zh) * 2020-06-12 2023-11-24 北京小米松果电子有限公司 一种图像增强模型的训练方法、装置及存储介质
US11257231B2 (en) * 2020-06-17 2022-02-22 Toyota Research Institute, Inc. Camera agnostic depth network
US11321859B2 (en) * 2020-06-22 2022-05-03 Toyota Research Institute, Inc. Pixel-wise residual pose estimation for monocular depth estimation
US11275959B2 (en) 2020-07-07 2022-03-15 Assa Abloy Ab Systems and methods for enrollment in a multispectral stereo facial recognition system
CN111881804B (zh) * 2020-07-22 2023-07-28 汇纳科技股份有限公司 基于联合训练的姿态估计模型训练方法、系统、介质及终端
CN111768438B (zh) * 2020-07-30 2023-11-24 腾讯科技（深圳）有限公司 一种图像处理方法、装置、设备以及计算机可读存储介质
TWI791261B (zh) * 2020-08-14 2023-02-01 宏達國際電子股份有限公司 在移動中提供虛擬環境的方法與系統以及非暫態電腦可讀取儲存媒體
JP7379299B2 (ja) * 2020-08-28 2023-11-14 株式会社東芝 位置姿勢推定装置、位置姿勢推定方法及びプログラム
CN114170290B (zh) * 2020-09-10 2025-08-01 华为技术有限公司 图像的处理方法及相关设备
KR102525583B1 (ko) * 2020-10-15 2023-04-26 한국전자기술연구원 경량형 증강현실장치의 스테레오 프레임을 이용한 3차원 맵을 생성하기 위한 장치 및 이를 위한 방법
KR102472568B1 (ko) * 2020-10-15 2022-12-01 한국전자기술연구원 포즈 정보와 뎁스 정보를 기초로 증강 현실을 제공하기 위한 3차원 맵을 구성하기 위한 장치 및 이를 위한 방법
US11868439B2 (en) * 2020-11-13 2024-01-09 Toyota Research Institute, Inc. Mixed-batch training of a multi-task network
US11734855B2 (en) * 2020-11-20 2023-08-22 Kabushiki Kaisha Toshiba Rotation equivariant orientation estimation for omnidirectional localization
WO2022123452A1 (en) * 2020-12-12 2022-06-16 Niantic, Inc. Self-supervised multi-frame monocular depth estimation model
KR20220085481A (ko) 2020-12-15 2022-06-22 삼성전자주식회사 영상 처리 방법 및 영상 처리 장치
CN114663575A (zh) * 2020-12-23 2022-06-24 日本电气株式会社 图像处理的方法、设备和计算机可读存储介质
KR102236240B1 (ko) * 2021-02-15 2021-04-05 주식회사 삼인공간정보 지형 형상 파일을 변환하는 장치
US20230260240A1 (en) * 2021-03-11 2023-08-17 Quintar, Inc. Alignment of 3d graphics extending beyond frame in augmented reality system with remote presentation
US11688090B2 (en) 2021-03-16 2023-06-27 Toyota Research Institute, Inc. Shared median-scaling metric for multi-camera self-supervised depth evaluation
US11361519B1 (en) * 2021-03-29 2022-06-14 Niantic, Inc. Interactable augmented and virtual reality experience
CN113160294B (zh) * 2021-03-31 2022-12-23 中国科学院深圳先进技术研究院 图像场景深度的估计方法、装置、终端设备和存储介质
CN113705309B (zh) * 2021-04-01 2025-04-11 腾讯科技（深圳）有限公司 一种景别类型判断方法、装置、电子设备和存储介质
US11961251B2 (en) * 2021-05-18 2024-04-16 Snap Inc. Continuous surface and depth estimation
TWI829167B (zh) * 2021-05-25 2024-01-11 美商尼安蒂克公司 用於採用小波分解之影像深度預測之方法及非暫時性電腦可讀儲存媒體
KR102489890B1 (ko) * 2021-05-28 2023-01-17 한국항공대학교산학협력단 깊이 추정 시스템 및 깊이 추정 방법
CN113470097B (zh) * 2021-05-28 2023-11-24 浙江大学 一种基于时域关联与姿态注意力的单目视频深度估计方法
KR20220123316A (ko) * 2021-06-08 2022-09-06 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 깊이 추정 모델의 트레이닝 방법, 장치, 전자 기기 및 저장 매체
US12555565B2 (en) 2021-09-30 2026-02-17 Samsung Electronics Co., Ltd. Device and method with target speaker identification
CN113591823B (zh) * 2021-10-08 2022-03-25 北京的卢深视科技有限公司 深度预测模型的训练及人脸深度图像的生成方法、装置
US12361647B2 (en) 2021-10-28 2025-07-15 Samsung Electronics Co., Ltd. System and method for depth and scene reconstruction for augmented reality or extended reality devices
CN116416481A (zh) * 2021-12-28 2023-07-11 中移(苏州)软件技术有限公司 单目图像深度预测模型训练方法、装置、设备及存储介质
KR102559936B1 (ko) * 2022-01-28 2023-07-27 포티투닷 주식회사 단안 카메라를 이용하여 깊이 정보를 추정하는 방법 및 장치
JP7666348B2 (ja) * 2022-02-08 2025-04-22 トヨタ自動車株式会社 情報処理装置
CN114549612A (zh) * 2022-02-25 2022-05-27 北京百度网讯科技有限公司 模型训练和图像处理方法、装置、设备及存储介质
US12190535B2 (en) * 2022-03-07 2025-01-07 Black Sesame Technologies Inc. Generating depth images for image data
US12347190B2 (en) * 2022-03-24 2025-07-01 Charter Communications Operating, Llc Efficient offloading of video frame processing tasks in edge-assisted augmented reality
US12058302B2 (en) * 2022-04-06 2024-08-06 Samsung Electronics Co., Ltd. Encoding depth information for images
CN114998411B (zh) * 2022-04-29 2024-01-09 中国科学院上海微系统与信息技术研究所 结合时空增强光度损失的自监督单目深度估计方法和装置
US12340530B2 (en) * 2022-05-27 2025-06-24 Toyota Research Institute, Inc. Photometric cost volumes for self-supervised depth estimation
US12380582B2 (en) * 2022-05-27 2025-08-05 Toyota Research Institute, Inc. Warping depth features for depth estimation
TWI881225B (zh) * 2022-06-02 2025-04-21 鴻海精密工業股份有限公司 一種深度估計方法、裝置、電子設備及存儲介質
CN116152321A (zh) * 2022-07-01 2023-05-23 马上消费金融股份有限公司 模型训练方法及装置、图像处理方法及装置
CN115345920A (zh) * 2022-08-03 2022-11-15 上海交通大学 场景深度重建方法、重建网络的训练方法、介质及设备
CN115827232B (zh) * 2022-12-08 2026-03-27 杭州王道控股有限公司 一种为业务模型确定配置的方法、装置、系统及设备
US12428022B2 (en) 2022-12-30 2025-09-30 Toyota Research Institute, Inc. Photometric masks for self-supervised depth learning
US12555255B2 (en) 2023-03-08 2026-02-17 Samsung Electronics Co., Ltd. Absolute depth estimation from a single image using online depth scale transfer
US20240371014A1 (en) * 2023-05-02 2024-11-07 Black Sesame Technologies Inc. Monocular depth estimation system
US12367648B2 (en) 2023-05-05 2025-07-22 Charter Communications Operating, Llc Optimizing image offloading in edge-assisted augmented reality
CN117115786B (zh) * 2023-10-23 2024-01-26 青岛哈尔滨工程大学创新发展中心 一种联合分割跟踪的深度估计模型训练方法及使用方法
FR3158575A1 (fr) * 2024-01-18 2025-07-25 Stellantis Auto Sas Procédé et dispositif de détermination d’une profondeur d’un pixel d’une image par un réseau de neurones associé à un système de vision embarqué dans un véhicule
FR3160798B1 (fr) * 2024-04-02 2026-02-13 Stellantis Auto Sas Procédé et dispositif d’apprentissage d’un modèle de prédiction de profondeur insensible à la présence d’objets dynamiques dans des images d’apprentissage.
US20250371761A1 (en) * 2024-05-29 2025-12-04 Niantic Spatial, Inc. Monocular depth estimation with geometry-informed depth hint
CN119478000A (zh) * 2024-11-04 2025-02-18 南京航空航天大学 一种基于CNN-Transformer混合架构的单目深度估计方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017129904A (ja) 2016-01-18 2017-07-27 ソニー株式会社 情報処理装置、情報処理方法、及び記録媒体

Family Cites Families (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2011188358A (ja) 2010-03-10 2011-09-22 Panasonic Corp Ｖｐｎ装置及びｉｐ通信装置
CN102223553B (zh) 2011-05-27 2013-03-20 山东大学 一种二维视频到三维视频的自动转换方法
US20130077820A1 (en) 2011-09-26 2013-03-28 Microsoft Corporation Machine learning gesture detection
US11263823B2 (en) 2012-02-24 2022-03-01 Matterport, Inc. Employing three-dimensional (3D) data predicted from two-dimensional (2D) images using neural networks for 3D modeling applications and other applications
US10262462B2 (en) * 2014-04-18 2019-04-16 Magic Leap, Inc. Systems and methods for augmented and virtual reality
US9275078B2 (en) 2013-09-05 2016-03-01 Ebay Inc. Estimating depth from a single image
JP6148154B2 (ja) * 2013-10-29 2017-06-14 日本電信電話株式会社 画像処理装置及び画像処理プログラム
JP5937709B1 (ja) 2015-01-29 2016-06-22 エヌ・ティ・ティ・コミュニケーションズ株式会社 通信制御装置、通信制御方法及び通信制御プログラム
JP6359985B2 (ja) 2015-02-12 2018-07-18 株式会社デンソーアイティーラボラトリ デプス推定モデル生成装置及びデプス推定装置
CN107438866B (zh) * 2015-05-13 2020-12-01 谷歌公司 深度立体：学习从现实世界形象预测新视图
US10255522B2 (en) * 2016-06-17 2019-04-09 Facebook, Inc. Generating object proposals using deep-learning models
CN114253400A (zh) * 2016-08-22 2022-03-29 奇跃公司 具有深度学习传感器的增强现实显示装置
US10466714B2 (en) * 2016-09-01 2019-11-05 Ford Global Technologies, Llc Depth map estimation with stereo images
GB2553782B (en) 2016-09-12 2021-10-20 Niantic Inc Predicting depth from image data using a statistical model
CN108629800A (zh) 2017-03-20 2018-10-09 北京三星通信技术研究有限公司 平面确定方法及增强现实显示信息的显示方法、相应装置
CN107067465A (zh) 2017-04-14 2017-08-18 深圳市唯特视科技有限公司 一种基于验证转换图像生成网络的三维视图合成方法
US10726514B2 (en) 2017-04-28 2020-07-28 Intel Corporation Compute optimizations for low precision machine learning operations
CN107204010B (zh) 2017-04-28 2019-11-19 中国科学院计算技术研究所 一种单目图像深度估计方法与系统
CN107578436B (zh) * 2017-08-02 2020-06-12 南京邮电大学 一种基于全卷积神经网络fcn的单目图像深度估计方法
CN107767413B (zh) * 2017-09-20 2020-02-18 华南理工大学 一种基于卷积神经网络的图像深度估计方法
US10803546B2 (en) * 2017-11-03 2020-10-13 Baidu Usa Llc Systems and methods for unsupervised learning of geometry from images using depth-normal consistency
EP3688718A1 (en) * 2017-11-15 2020-08-05 Google LLC Unsupervised learning of image depth and ego-motion prediction neural networks
CN107909150B (zh) 2017-11-29 2020-08-18 华中科技大学 基于逐块随机梯度下降法在线训练cnn的方法与系统
US11182917B2 (en) * 2017-12-08 2021-11-23 Baidu Usa Llc Stereo camera depth determination using hardware accelerator
US10810754B2 (en) * 2018-04-24 2020-10-20 Ford Global Technologies, Llc Simultaneous localization and mapping constraints in generative adversarial networks for monocular depth estimation
WO2019222467A1 (en) * 2018-05-17 2019-11-21 Niantic, Inc. Self-supervised training of a depth estimation system
CN109191514B (zh) 2018-10-23 2020-11-24 北京字节跳动网络技术有限公司 用于生成深度检测模型的方法和装置
US11044462B2 (en) 2019-05-02 2021-06-22 Niantic, Inc. Self-supervised training of a depth estimation model using depth hints

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017129904A (ja) 2016-01-18 2017-07-27 ソニー株式会社 情報処理装置、情報処理方法、及び記録媒体

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Tinghui Zhou, et al.，Unsupervised Learning of Depth and Ego-Motion from Video，2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)，米国，2017年，https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8100183

Also Published As

Publication number Publication date
AU2019270095B2 (en) 2024-06-27
CN112534475A (zh) 2021-03-19
EP3794555B1 (en) 2024-03-13
KR102506959B1 (ko) 2023-03-07
US11991342B2 (en) 2024-05-21
TW202004670A (zh) 2020-01-16
AU2019270095A1 (en) 2021-01-14
EP3794555A1 (en) 2021-03-24
CN112534475B (zh) 2023-01-10
TWI790380B (zh) 2023-01-21
CA3100640A1 (en) 2019-11-21
WO2019222467A8 (en) 2020-03-26
JP2021526680A (ja) 2021-10-07
WO2019222467A1 (en) 2019-11-21
AU2019270095B9 (en) 2024-11-14
US20210314550A1 (en) 2021-10-07
US20240340400A1 (en) 2024-10-10
KR20200146040A (ko) 2020-12-31
EP3794555A4 (en) 2021-06-09
US11082681B2 (en) 2021-08-03
US20190356905A1 (en) 2019-11-21
CA3100640C (en) 2023-04-18

Similar Documents

Publication Publication Date Title
JP7241775B2 (ja) 深度推定システムの自己教師ありトレーニング
JP7174139B2 (ja) 深度ヒントを使用した深度推定モデルの自己教師ありトレーニング
TWI829167B (zh) 用於採用小波分解之影像深度預測之方法及非暫時性電腦可讀儲存媒體
US20240185478A1 (en) Virtual Occlusion Mask Prediction Through Implicit Depth Estimation

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20210114

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220414

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20220414

A871 Explanation of circumstances concerning accelerated examination

Free format text: JAPANESE INTERMEDIATE CODE: A871

Effective date: 20220414

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20220804

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20220913

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20221209

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20230221

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20230307

R150 Certificate of patent or registration of utility model

Ref document number: 7241775

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250