CN117021098B - Method for generating world-place action based on in-place action - Google Patents
Method for generating world-place action based on in-place action Download PDFInfo
- Publication number
- CN117021098B CN117021098B CN202311057670.2A CN202311057670A CN117021098B CN 117021098 B CN117021098 B CN 117021098B CN 202311057670 A CN202311057670 A CN 202311057670A CN 117021098 B CN117021098 B CN 117021098B
- Authority
- CN
- China
- Prior art keywords
- frame
- joint
- acceleration
- displacement
- pelvis
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000009471 action Effects 0.000 title claims abstract description 32
- 230000001133 acceleration Effects 0.000 claims abstract description 53
- 230000033001 locomotion Effects 0.000 claims abstract description 46
- 238000006073 displacement reaction Methods 0.000 claims abstract description 45
- 210000004197 pelvis Anatomy 0.000 claims abstract description 43
- 230000008859 change Effects 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000003139 buffering effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 7
- 210000001226 toe joint Anatomy 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000036541 health Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 210000003108 foot joint Anatomy 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 210000003141 lower extremity Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000005293 physical law Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Processing Or Creating Images (AREA)
Abstract
A method for generating a world-place action based on an in-place action, comprising the steps of: step one: inputting an in-place frame sequence, and setting a fixed delay buffer; step two: calculating pelvis displacements of the motion of all buffered frames based on the first ground assumption and calculating acceleration and acceleration derivatives of pelvis joint motion; step three: judging whether the current frame is a jump starting frame, if not, outputting a result, if so, starting to change the state from the frame, traversing the buffer memory to identify a jump landing frame, and calculating the pelvis joint displacement of the jump frame sequence according to the duration of the start and stop frame and the acceleration and the speed of the start frame. The invention provides a method for generating a world-position from an in-position. The method solves the bottleneck problem that the accurate motion displacement according with physics requires manual production: and generating the world-position data with the physical rule from the in-position action in real time.
Description
Technical Field
The invention belongs to the field of World-plane motion generation, and particularly relates to a method for generating World-plane motion based on in-plane motion.
Background
in-position motion refers to a motion performed at the same position, i.e., a motion of an object or a human body at one position. For example, when a person walks, his body will move on the same location, which is the in-place motion. In contrast, world-motion refers to the movement of an object or body in different positions. The generation of a world-plan motion from an in-plan motion is a very promising theme. Virtual Reality (VR) and Augmented Reality (AR) in which human motion is critical to achieving an immersive experience. Converting in-place human actions into world-place human actions can help develop more realistic virtual characters, thereby improving user experience. Robot control: the in-position motion data are converted into world-position motion data, and the method can be used for motion planning and control of the robot, so that the robot can adapt to different environments and task requirements. The in-position motion data are converted into world-position motion data, so that the threshold of human body motion analysis and health monitoring can be reduced, accurate displacement information can be obtained by using a simple gesture estimation sensor, and the health condition and the functional state of a human body can be known by analyzing the motion track and gesture information of the human body at different positions. In the field of games, the method can greatly reduce the cost of motion production, reduce motion control logic, promote the speed of physical simulation and animation production in game development and improve the sense of reality and playability of the games.
In the conventional world-motion manufacturing process, the displacement is often required to be manufactured manually. Although motion capture and other techniques can also be used to conveniently produce motion containing displacement data, the displacement data obtained by direct capture often has a lot of noise and even errors, and requires a lot of subsequent manual data processing, which is still not intelligent enough. Especially in the current trend of AI, the requirement of large-scale action data sets is urgent, but the bottleneck of manual production seriously affects the production efficiency.
Disclosure of Invention
The invention provides a method for generating a world-place action based on an in-place action, which is used for solving the defects in the prior art.
The invention is realized by the following technical scheme:
a method for generating a world-place action based on an in-place action, comprising the steps of:
step one: preprocessing frame data: first, joint global motion data is calculated from joint local motion data.
The method of calculating global data from local data is as follows:
P global ＝R father *P local +P father
R global ＝R father *R local
wherein P is global Is to calculate global displacement of the joint, R global To calculate the global attitude rotation value of the joint, R father Is global attitude rotation value, P of father joint father For global displacement of the parent joint, P local To calculate the local displacement data of the joint under the father joint, R local To calculate the local pose rotation value of the joint under the parent joint. Global data of all joints are recursively calculated.
Step two, a step two is carried out; based on the first ground assumption that each frame of motion accords with ground constraint, generating displacement data of all frames, and discretizing to calculate the acceleration and acceleration derivative of the generated pelvis joint, wherein the calculation formula is as follows:
where P represents pelvis displacement, v represents velocity, a represents acceleration,representing the derivative of acceleration, frameRate representing the animation data frame rate;
step three: judging whether the current frame is a jump starting frame, if not, outputting a result, if so, starting to change a state from the frame, traversing a cache to identify a jump landing frame, and calculating pelvis joint displacement of a jump frame sequence according to the duration of the start and stop frame and the acceleration and speed of the start frame;
calculating the ground free constraint according to the start and stop frame acceleration and speed:
wherein P is n For displacement of the pelvis joint of the nth frame during no ground constraint,and->The resolved displacements of the pelvis joint in the vertical and horizontal planes, respectively. />And->Respectively representing the horizontal displacement and the velocity of the pelvis joint of the start frame of the non-ground-constrained process, t representing the offset time from the start frame of the non-ground-constrained process to the nth frame,and->Respectively representing the displacement and the velocity of the initial frame pelvis joint in the vertical direction of the ground free constraint process, and g represents the standard gravitational acceleration.
In the method for generating the world-plan action based on the in-plan action, the caching principle in the first step is that 18 frames are needed for 30 frames/second of animation caching, and 36 frames are needed for 60 frames/second of animation data caching.
The method for generating the world-place action based on the in-place action as described above, wherein the pelvis displacement of each frame in the second step may be expressed as:
in the third step, the jump start and stop frame is judged by using the acceleration value and the acceleration derivative of the pelvis joint, and the judgment formula is as follows:
wherein a is n For the acceleration of the nth frame pelvis joint generated in step one,is the derivative of acceleration for the nth frame. a, a 0 And d 0 Respectively counting the obtained acceleration detection threshold value and the acceleration derivative detection threshold value, and counting the obtained acceleration detection threshold value and the obtained acceleration derivative detection threshold value when a is 0 ＝32.5、d 0 When=15, the best detection effect is achieved.
If f (a) n ) If > 0, this frame is ground constrained, if f (a n ) And > 0 indicates that the frame is unconstrained.
The invention has the advantages that: the invention provides a method for generating a world-position from an in-position. The method solves the bottleneck problem that the accurate motion displacement according with physics requires manual production: and generating the world-position data with the physical rule from the in-position action in real time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it will be obvious that the drawings in the following description are some embodiments of the present invention, and that other drawings can be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a schematic flow chart of the present invention;
fig. 2 is a schematic view of the plantar joint of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, a method for generating a wotld-place action based on an in-place action includes the following steps:
step one: preprocessing frame data: first, joint global motion data is calculated from joint local motion data.
The method of calculating global data from local data is as follows:
P global ＝R father *P local +P father
R global ＝R father *R local
wherein P is global Is to calculate global displacement of the joint, R global To calculate the global attitude rotation value of the joint, R father Is global attitude rotation value, P of father joint father For global displacement of the parent joint, P local To calculate the local displacement data of the joint under the father joint, R local To calculate the local pose rotation value of the joint under the parent joint. Global data of all joints are recursively calculated.
Step two, a step two is carried out; based on the first ground assumption that each frame of motion accords with ground constraint, generating displacement data of all frames, and discretizing to calculate the acceleration and acceleration derivative of the generated pelvis joint, wherein the calculation formula is as follows:
where P represents pelvis displacement, v represents velocity, a represents acceleration,representing the derivative of acceleration, frameRate representing the animation data frame rate;
step three: judging whether the current frame is a jump starting frame, if not, outputting a result, if so, starting to change a state from the frame, traversing a cache to identify a jump landing frame, and calculating pelvis joint displacement of a jump frame sequence according to the duration of the start and stop frame and the acceleration and speed of the start frame;
calculating the ground free constraint according to the start and stop frame acceleration and speed:
where Pn is the displacement of the pelvis joint of the nth frame during no ground constraint,and->The resolved displacements of the pelvis joint in the vertical and horizontal planes, respectively. />And->Respectively representing the horizontal displacement and the velocity of the pelvis joint of the start frame of the non-ground-constrained process, t representing the offset time from the start frame of the non-ground-constrained process to the nth frame,and->Respectively representing the displacement and the velocity of the initial frame pelvis joint in the vertical direction of the ground free constraint process, and g represents the standard gravitational acceleration.
Specifically, in the first step described in this embodiment, the buffering principle is that 18 frames are required for buffering 30 frames/second of animation, and 36 frames are required for buffering 60 frames/second of animation data. The motion of the human body is limited by natural attributes, the motion is limited, the dead time of most human body motion is less than 0.6s through data analysis, the data is used as standard to design the frame buffer length, the buffer of the animation of 30 frames/second needs 18 frames, the buffer of the animation of 60 frames/second needs 36 frames, and the like if the number of frames per second increases.
Specifically, the pelvis displacement of each frame in the second step described in this embodiment may be expressed as:
preferably, the above formula for determining pelvis displacement is derived as follows:
the invention proposes the assumption based on the observation of data and the analysis of realistic physical actions: all movements supported by the lower limbs are produced by the foot as a point of force. According to this assumption, there are three situations in which the ground is in contact, namely, no ground constraint, one-foot ground constraint, and two-foot ground constraint. Several studies have also proposed similar assumptions and used machine learning methods to classify frames of in-place motion to identify several constraints. However, this classification is limited by statistical methods, which make it difficult to achieve near 100% accuracy, and thus the final effect is limited to specific actions such as walking. Through analysis, the invention can obtain a new conclusion, greatly reduce the workload of the problem, and remarkably improve the calculation speed to realize real-time operation.
First neglecting the "wane" of the sole"switch problem, animation clips all start in standing position, so frame 1 is a two-foot ground constraint. Let the coordinates of the joints of the left and right feet be respectively the sumThen in frame 2, three cases constraint scenarios are possible. Assuming frame 2 is still a bipedal constraint, then +.> Remain unchanged; if the 2 nd frame is a single foot constraint, there are two possibilities that the left foot remains constrained, then the left foot position remains +.>The right foot position is obtained according to the left foot constraint and by using other calculation methods, if the right foot keeps the constraint position +.>The left foot position can be calculated using the same method; if the 2 nd frame is free from ground constraint, calculating the position according to the frame before taking off, assuming that the calculated pelvis joint movement speed according to the calculated frame sequence is +.>The position of the pelvis joint of the second frame is +.>The synthesis can be expressed as:
wherein the method comprises the steps ofAnd->The vectors of the root joint to the pelvis joint are represented respectively, and α and β represent weighting coefficients, the sum of which is 1. Because in-place motion is a trusted correct action, therefore +.>And->Is equal, in which case the bipedal constraint may be expressed in the form of a monopedal constraint. Thus equation (1) can be expressed as:
each frame depends on the position of the previous frame, the position of the N frame depends on the N-1 frame, and the frame always falls over
Push to frame 0. Derived from this precondition to all frames:
in addition, regarding the "rocker" problem of the sole, the "rocker" is a metaphor description of the sole of a human body, and as shown in fig. 2, the human foot is often abstract in a virtual space to be a connection relationship as illustrated.
The foot joint is not in direct contact with the ground, and the displacement is indirectly obtained through the constraint of the heel or toe joint and the ground. There are also three possibilities for ground constraint, just toe joint ground constraint, just heel joint ground constraint or toe and heel simultaneous ground constraint, respectively. Can be expressed as:
wherein the method comprises the steps ofAnd->Is consistent and can therefore be expressed as:
in the process of contacting the sole of the foot with the ground, most of the foot and heel are simultaneously contacted with the ground constraint, and the toe joint single joint constraint can be used for replacing calculation. Through statistics, the situation of individual ground constraint of the heel joint is often in the conversion process of two types of constraint, and the constraint is unstable, so that the joint can be quickly transited to the toe and heel joint common ground constraint or the toe individual ground constraint. The ground constraint of the heel joint can be ignored and treated as either unconstrained or the toe joint alone ground constraint. Formulation of formulas
The method comprises the following steps:
the experiment shows that the processing effect is good, the generated displacement is not adversely affected, and the calculation process and the judgment of state switching are greatly simplified.
The preprocessing of in-place motion data in the second step of the invention is based on an assumption that: assume that each frame action belongs to a ground constraint. From the above, it is deduced that each frame belongs to the monopod ground constraint. Thus, the displacement of each frame can be expressed as:
further, in the third step described in this embodiment, the jump start and stop frame is determined by using the acceleration value and the derivative of the acceleration of the pelvis joint, and the determination formula is as follows:
if f (a) 0 ) If > 0, this frame is ground constrained, if f (a 0 ) And less than or equal to 0 indicates that the frame is in an unconstrained state.
Preferably, the human body movement needs to conform to the physical laws, and the movement of the pelvis joint is derived from interaction of the foot and the ground. Jumping of the human body requires a force accumulation and landing also requires a buffer to unload the force, so the motion acceleration of pelvis should be smooth according to newton's law. In the step one preprocessing, it is assumed that all motions belong to the ground constraint, and if the frame motion data does not conform to the ground constraint, the pelvis joint acceleration is necessarily not smooth. The skipped frame sequence can thus be determined by analyzing the acceleration of the pelvis joint of the data that completes the step one preprocessing. From a large number of statistical data and mathematical calculations we have found a method for determining the jump start and stop frames by determining the acceleration value and the acceleration derivative of the pelvis joint, expressed by the formula:
wherein a is n For the acceleration of the nth frame pelvis joint generated in step one,is the derivative of acceleration for the nth frame. a, a 0 And d 0 Respectively counting the obtained acceleration detection threshold value and the acceleration derivative detection threshold value, and counting the obtained acceleration detection threshold value and the obtained acceleration derivative detection threshold value when a is 0 ＝32.5、d 0 When=15, the best detection effect is achieved.
If f (a) n ) If > 0, this frame is ground constrained, if f (a n ) And > 0 indicates that the frame is unconstrained.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solution of the present invention, and not limiting thereof; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (3)
1. A method for generating a world-place action based on an in-place action is characterized by comprising the following steps: the method comprises the following steps:
step one: preprocessing frame data: firstly, calculating joint global action data according to the joint local action data;
the method of calculating global data from local data is as follows:
P global ＝R father *P local +P father
R global ＝P father *R local
wherein P is global Is to calculate global displacement of the joint, R global To calculate the global attitude rotation value of the joint, R father Is global attitude rotation value, P of father joint father For global displacement of the parent joint, P local To calculate the local displacement data of the joint under the father joint, R local Calculating global data of all joints in a recursion mode for calculating a local posture rotation value of the joint under a father joint;
step two, a step two is carried out; based on the first ground assumption that each frame of motion accords with ground constraint, generating displacement data of all frames, and discretizing to calculate the acceleration and acceleration derivative of the generated pelvis joint, wherein the calculation formula is as follows:
where P represents pelvis displacement, v represents velocity, a represents acceleration,representing the derivative of acceleration, frameRate representing the animation data frame rate;
the pelvis displacement for each frame in the above steps is expressed as:
wherein the method comprises the steps ofAnd->Vectors respectively representing the root joint to the pelvis joint;
step three: judging whether the current frame is a jump starting frame, if not, outputting a result, if so, starting to change a state from the frame, traversing a cache to identify a jump landing frame, and calculating pelvis joint displacement of a jump frame sequence according to the duration of the start and stop frame and the acceleration and speed of the start frame;
calculating the ground free constraint according to the start and stop frame acceleration and speed:
wherein P is n For displacement of the pelvis joint of the nth frame during no ground constraint,and->The decomposed displacement of pelvis joint in the vertical direction and the horizontal plane are respectively +.>And->Respectively representing the horizontal displacement and the velocity of the pelvis joint of the start frame of the non-ground-constrained process, t representing the offset time from the start frame of the non-ground-constrained process to the nth frame,and->Respectively representing the displacement and the velocity of the initial frame pelvis joint in the vertical direction of the ground free constraint process, and g represents the standard gravitational acceleration.
2. The method for generating a world-place action based on an in-place action according to claim 1, wherein: in the first step, the buffering principle is that 18 frames are needed for buffering 30 frames/second of animation, and 36 frames are needed for buffering 60 frames/second of animation data.
3. The method for generating a world-place action based on an in-place action according to claim 1, wherein: in the third step, the jump start and stop frame is judged by using the acceleration value and the acceleration derivative of the pelvis joint, and the judgment formula is as follows:
wherein a is n For the acceleration of the nth frame pelvis joint generated in step one,a is the derivative of acceleration of the nth frame 0 And d 0 Respectively counting the obtained acceleration detection threshold value and the acceleration derivative detection threshold value, and counting the obtained acceleration detection threshold value and the obtained acceleration derivative detection threshold value when a is 0 ＝32.5、d 0 When the detection result is 15, the optimal detection effect is achieved;
if f (a) n )>0, then indicates that the frame is ground constrained, if f (a n )>0 indicates that the frame is in an unconstrained state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311057670.2A CN117021098B (en) | 2023-08-22 | 2023-08-22 | Method for generating world-place action based on in-place action |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311057670.2A CN117021098B (en) | 2023-08-22 | 2023-08-22 | Method for generating world-place action based on in-place action |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117021098A CN117021098A (en) | 2023-11-10 |
| CN117021098B true CN117021098B (en) | 2024-01-23 |
Family
ID=88644768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311057670.2A Active CN117021098B (en) | 2023-08-22 | 2023-08-22 | Method for generating world-place action based on in-place action |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117021098B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6144385A (en) * | 1994-08-25 | 2000-11-07 | Michael J. Girard | Step-driven character animation derived from animation data without footstep information |
| KR20010057880A (en) * | 1999-12-23 | 2001-07-05 | 오길록 | Animation method for walking motion variation |
| KR101519775B1 (en) * | 2014-01-13 | 2015-05-12 | 인천대학교 산학협력단 | Method and apparatus for generating animation based on object motion |
| CN112891947A (en) * | 2021-04-02 | 2021-06-04 | 网易（杭州）网络有限公司 | Jumping animation processing method and device, electronic equipment and computer readable medium |
| CN114998487A (en) * | 2022-05-07 | 2022-09-02 | 广州虎牙科技有限公司 | Animation generation method, device, equipment and readable medium |
| CN115546247A (en) * | 2022-10-21 | 2022-12-30 | 北京中科深智科技有限公司 | Motion capture method based on LightHouse positioning system |
| WO2023000916A1 (en) * | 2021-07-23 | 2023-01-26 | 网易（杭州）网络有限公司 | Jump control method and apparatus for characters in game, terminal device, and medium |
| CN115888101A (en) * | 2022-12-02 | 2023-04-04 | 网易（杭州）网络有限公司 | Virtual role state switching method and device, storage medium and electronic equipment |
| CN116543080A (en) * | 2023-05-06 | 2023-08-04 | 广州时秤信息技术有限公司 | Animation processing method and device based on root bones |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019226554A1 (en) * | 2018-05-22 | 2019-11-28 | Magic Leap, Inc. | Skeletal systems for animating virtual avatars |
-
2023
- 2023-08-22 CN CN202311057670.2A patent/CN117021098B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6144385A (en) * | 1994-08-25 | 2000-11-07 | Michael J. Girard | Step-driven character animation derived from animation data without footstep information |
| KR20010057880A (en) * | 1999-12-23 | 2001-07-05 | 오길록 | Animation method for walking motion variation |
| KR101519775B1 (en) * | 2014-01-13 | 2015-05-12 | 인천대학교 산학협력단 | Method and apparatus for generating animation based on object motion |
| CN112891947A (en) * | 2021-04-02 | 2021-06-04 | 网易（杭州）网络有限公司 | Jumping animation processing method and device, electronic equipment and computer readable medium |
| WO2023000916A1 (en) * | 2021-07-23 | 2023-01-26 | 网易（杭州）网络有限公司 | Jump control method and apparatus for characters in game, terminal device, and medium |
| CN114998487A (en) * | 2022-05-07 | 2022-09-02 | 广州虎牙科技有限公司 | Animation generation method, device, equipment and readable medium |
| CN115546247A (en) * | 2022-10-21 | 2022-12-30 | 北京中科深智科技有限公司 | Motion capture method based on LightHouse positioning system |
| CN115888101A (en) * | 2022-12-02 | 2023-04-04 | 网易（杭州）网络有限公司 | Virtual role state switching method and device, storage medium and electronic equipment |
| CN116543080A (en) * | 2023-05-06 | 2023-08-04 | 广州时秤信息技术有限公司 | Animation processing method and device based on root bones |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117021098A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8953844B2 (en) | System for fast, probabilistic skeletal tracking | |
| US11217003B2 (en) | Enhanced pose generation based on conditional modeling of inverse kinematics | |
| WO2021143289A1 (en) | Animation processing method and apparatus, and computer storage medium and electronic device | |
| US9058663B2 (en) | Modeling human-human interactions for monocular 3D pose estimation | |
| US11992768B2 (en) | Enhanced pose generation based on generative modeling | |
| US11995754B2 (en) | Enhanced animation generation based on motion matching using local bone phases | |
| CN111488824A (en) | Motion prompting method and device, electronic equipment and storage medium | |
| TWI427558B (en) | System for estimating location of occluded skeleton, method for estimating location of occluded skeleton and method for reconstructing occluded skeleton | |
| US11670030B2 (en) | Enhanced animation generation based on video with local phase | |
| CN111223168A (en) | Target object control method and device, storage medium and computer equipment | |
| Lin et al. | Balancing and reconstruction of segmented postures for humanoid robots in imitation of motion | |
| US11830121B1 (en) | Neural animation layering for synthesizing martial arts movements | |
| CN117021098B (en) | Method for generating world-place action based on in-place action | |
| JP2011170857A (en) | System and method for performing motion recognition with minimum delay | |
| Jiang et al. | EgoPoser: Robust Real-Time Ego-Body Pose Estimation in Large Scenes | |
| CN101952879A (en) | Methods and apparatus for designing animatronics units from articulated computer generated characters | |
| CN115294228A (en) | Multi-graph human body posture generation method and device based on modal guidance | |
| Liu et al. | Performance-based control interfaces using mixture of factor analyzers | |
| Du et al. | 3D hand model fitting for virtual keyboard system | |
| US20230083619A1 (en) | Method and system of global position prediction for imu motion capture | |
| KR101547208B1 (en) | Apparatus and method for reconstructing whole-body motion using wrist trajectories | |
| Huang et al. | CoMo: Controllable Motion Generation through Language Guided Pose Code Editing | |
| Lin et al. | Animating rising up from various lying postures and environments | |
| Kleine Deters | Therapeutic exercise assessment automation, a hidden Markov model approach. | |
| US20230310998A1 (en) | Learning character motion alignment with periodic autoencoders |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Room 911, 9th Floor, Block B, Xingdi Center, Building 2, No.10, Jiuxianqiao North Road, Jiangtai Township, Chaoyang District, Beijing, 100000 Patentee after: Beijing Zhongke Shenzhi Technology Co.,Ltd. Country or region after: China Address before: 100000 room 311a, floor 3, building 4, courtyard 4, Yongchang Middle Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee before: Beijing Zhongke Shenzhi Technology Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |