pith. sign in

arxiv: 2606.21162 · v2 · pith:XLJH7H3Anew · submitted 2026-06-19 · 💻 cs.GR · cs.CV

PIAvatar: Physically Interactive Avatars via Deformation Gradient Decoupling

Sang-Hun Han , Min-Gyu Park , Jisu Shin , Seunghyun Shin , Jin-Hwi Park , Hae-Gon Jeon This is my paper

Pith reviewed 2026-07-01 07:25 UTC · model grok-4.3

classification 💻 cs.GR cs.CV
keywords physically interactive avatarsdeformation gradient decouplingMaterial Point Methodnon-rigid body simulationhuman-object interactionskeletal pose tracking3D human avatars
0
0 comments X

The pith

Decoupling kinematic velocity from deformation gradient lets 3D avatars handle physical forces while reaching desired poses.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a method to give 3D human avatars the ability to interact physically with objects and other avatars while undergoing non-rigid deformations. Existing pose-driven models produce visually convincing bodies but restrict how those bodies respond to contact forces. The central move is to separate kinematic velocity from the deformation gradient so that external forces do not create stresses that block the intended pose. A skeletal structure is embedded to recover poses in closed form even while the body deforms, and the whole system runs inside a Material Point Method solver to keep the motion physically consistent.

Core claim

When external forces act on avatars, the kinematic velocity induces stress which hinders the avatar's ability to achieve a desired pose. Decoupling kinematic velocity from the deformation gradient removes this obstruction. A skeletal framework integrated within the avatar enables closed-form pose estimation and real-time tracking during non-rigid physical interactions. The approach is realized inside a conventional Material Point Method framework, producing physically consistent dynamics for both avatar-object and avatar-avatar contact.

What carries the argument

Deformation gradient decoupling, which isolates kinematic velocity so that external forces no longer generate blocking stresses on the target pose.

If this is right

  • Avatars can sustain non-rigid deformations during sustained contact with objects or other avatars.
  • Pose estimation remains available in closed form throughout the interaction.
  • Dynamics remain consistent with the Material Point Method across human-object and human-human cases.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same separation of velocity components could be tested on non-human characters whose surface meshes are driven by different underlying rigs.
  • Extending the skeletal tracker to multi-character scenes would require checking whether inter-avatar collisions still preserve the closed-form property.
  • If the decoupling holds, it should be possible to replace the Material Point Method solver with another continuum solver without changing the kinematic-deformation split.

Load-bearing premise

A skeletal framework integrated within the avatar allows estimating its poses and real-time tracking in a closed form even during non-rigid physical interactions.

What would settle it

Demonstrate an interaction scenario in which the tracked skeletal poses deviate from closed-form solutions or the avatar fails to reach its commanded pose under measured external forces.

Figures

Figures reproduced from arXiv: 2606.21162 by Hae-Gon Jeon, Jin-Hwi Park, Jisu Shin, Min-Gyu Park, Sang-Hun Han, Seunghyun Shin.

Figure 1
Figure 1. Figure 1: Physical avatar interactions with bidirectional and non-rigid defor [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: An illustration of our framework. (a) To faithfully reflect the user-defined motion, we decouple the kinematic velocity from the deformation gradient update (Sec. 4.1). (b) By computing the velocity from the transformations of the embedded skeletal structure, our method preserves the pose consistency throughout the simulation (Sec. 4.2). 4.1 Kinematic Deformation Decoupling (a) Velocity (b) Deformation (c)… view at source ↗
Figure 3
Figure 3. Figure 3: Velocity-induced stress formation. (a) The kinematic velocity is applied to the avatar par￾ticles p. (b) The change in deformation gradients F p occurs due to the kinematic velocity (see blue- and red-colored ellipses). (c) The deformation generates stress σp that hinders intended kinematic motion. As shown in [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Various Interactions. (a, b) Non-rigid deformations arising from physical interactions with objects. (c, d) The bidirectional interaction between avatars and its mutual pose changes. Time and Space Complexity. The detailed runtime is described in Tab. 3. The experiments are conducted using single- and four-avatar scenarios in SMPL￾X and AG. The velocity generation and the Kabsch algorithm are executed once… view at source ↗
Figure 5
Figure 5. Figure 5: Non-rigid deformation. Our method can generate non-rigid deformations, such as naturally fluttering hair, that are not achievable with conventional avatars without explicit modeling. Human-Human Interactions. In [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Soft-tissue deformable avatar. Our simulator produces non-rigid effects, such as the natural jiggling of belly fat. Unlike conventional LBS-based avatars, where body motion does not influence surface deformation, our physical simulation system exhibits natural inertial wobbling during jumping and landing [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Deformation gradient visualization. The simulation visualizes how forces are transmitted through changes in the deformation gradient F p. the hitting point of the object, the deformation gradient progressively propagates outward to the surrounding area. Simulation on Resistance of Avatar. To highlight the effectiveness of our PIAvatar, we design one more scenario where a ball, set in motion by one avatar’s… view at source ↗
Figure 8
Figure 8. Figure 8: Resistance simulation according to the impact of the ball. [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
Figure 8
Figure 8. Figure 8: Heterogeneous material assignment. (a) The body (Neo-Hookean, E=105 ) and compliant regions (corotated, E=102 –103 ) exhibit distinct deformation magnitudes under motion. (b) Despite regional variation in stiffness, global skeletal articulation remains stable and consistent with the input pose sequence. Heterogeneous Material Parameters. We lastly evaluate the versatility of our PIAvatar through an experim… view at source ↗
Figure 9
Figure 9. Figure 9: Heterogeneous material assignment. (a) The body (Neo-Hookean, E=105 ) and compliant regions (corotated, E=102 –103 ) exhibit distinct deformation magnitudes under motion. (b) Despite regional variation in stiffness, global skeletal articulation remains stable and consistent with the input pose sequence. 6 Conclusion We introduce PIAvatar, an MPM-based avatar simulation framework that achieves physically aw… view at source ↗
Figure 10
Figure 10. Figure 10: Motivation for our disentangled deformation gradient. [PITH_FULL_IMAGE:figures/full_fig_p016_10.png] view at source ↗
Figure 10
Figure 10. Figure 10: Loose-garment simulation. On spin and jump from fast AMASS motion sequences, our coupled cloth solver produces visible flutter and asymmetric billowing of the garment driven by rapid body articulation. 5.5 Loose Cloth Simulation Existing LBS-based avatars deform garments using skinning weights inherited from the underlying body, so loose clothing rigidly follows the skin and cannot exhibit secondary dynam… view at source ↗
Figure 11
Figure 11. Figure 11: Effect of Young’s modulus E on object stiffness. (a) High-E objects behave as rigid masses and move as solid blocks. (b) Low-E objects deform noticeably and fly in a soft, squishy manner. These results demonstrate that our simulator natu￾rally reflects material-dependent stiffness [PITH_FULL_IMAGE:figures/full_fig_p019_11.png] view at source ↗
Figure 11
Figure 11. Figure 11: Motivation for our disentangled deformation gradient. [PITH_FULL_IMAGE:figures/full_fig_p016_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Multi-object interactions. The avatar and objects push against each other, causing object deformation. Our simulator supports such interactions between an avatar and multiple dynamic objects, demonstrating multi-object capabilities. References 1. Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM Transactions on Graphics (T… view at source ↗
Figure 13
Figure 13. Figure 13: Interaction response under different object masses. [PITH_FULL_IMAGE:figures/full_fig_p020_13.png] view at source ↗
Figure 14
Figure 14. Figure 14: Effect of Young’s modulus E on object stiffness. (a) High-E objects behave as rigid masses and move as solid blocks. (b) Low-E objects deform noticeably and fly in a soft, squishy manner. These results demonstrate that our simulator natu￾rally reflects material-dependent stiffness [PITH_FULL_IMAGE:figures/full_fig_p021_14.png] view at source ↗
Figure 15
Figure 15. Figure 15: Multi-object interactions. The avatar and objects push against each other, causing object deformation. Our simulator supports such interactions between an avatar and multiple dynamic objects, demonstrating multi-object capabilities. Multi-object Interaction [PITH_FULL_IMAGE:figures/full_fig_p021_15.png] view at source ↗
Figure 16
Figure 16. Figure 16: Interaction response under different object masses. [PITH_FULL_IMAGE:figures/full_fig_p022_16.png] view at source ↗
Figure 17
Figure 17. Figure 17: Resistance simulation according to the impact of the ball. [PITH_FULL_IMAGE:figures/full_fig_p022_17.png] view at source ↗
read the original abstract

3D human avatars have shown impressive visual fidelity driven by pose-conditioned models, yet they still lack the physical ability required for interactions with each other and environments. Although recent studies have made various attempts to incorporate physical characteristics into 3D avatars, they only exhibit limited physical deformations, often leading to constrained interaction behaviors. To resolve this issue, we present PIAvatar, a framework to simultaneously enable physically aware interactions between avatar-avatar and avatar-environment, and a non-rigid deformable human body simulation. In this work, our key insight is to decouple kinematic velocity from deformation gradient. When external forces act on avatars, the kinematic velocity induces stress which hinders the avatar's ability to achieve a desired pose. In addition, we integrate a skeletal framework within the avatar. It allows estimating its poses and real-time tracking in a closed form, even during non-rigid physical interactions. Our approach is implemented within a conventional Material Point Method framework to ensure physically consistent dynamics. We lastly evaluate the method on both human-object and human-human interaction scenarios to assess its behavior under diverse interaction settings.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The paper presents PIAvatar, a framework for physically interactive 3D human avatars that supports avatar-avatar and avatar-environment interactions alongside non-rigid body deformations. The central technical claim is that decoupling kinematic velocity from the deformation gradient within a Material Point Method (MPM) simulation prevents external forces from inducing stress that blocks desired poses; additionally, an integrated skeletal framework is asserted to enable closed-form pose estimation and real-time tracking even under non-rigid physical interactions.

Significance. If the decoupling and closed-form skeletal integration can be shown to hold under MPM dynamics, the work would address a recognized limitation in current pose-conditioned avatar models by enabling physically consistent, interactive deformations at interactive rates.

major comments (2)
  1. [Abstract] Abstract: the assertion that the skeletal framework 'allows estimating its poses and real-time tracking in a closed form, even during non-rigid physical interactions' is load-bearing for the central claim yet unsupported by any derivation, equation, or algorithmic description. Non-rigid MPM particle motion alters effective bone attachments, converting skeletal recovery into an inverse problem that normally requires optimization; without an explicit closed-form map that remains valid post-deformation, the ability to achieve desired poses under external forces cannot be verified.
  2. [Abstract] Abstract: the key insight of decoupling kinematic velocity from deformation gradient is stated without accompanying equations or MPM update rules. It is therefore impossible to assess whether the decoupling is parameter-free, whether it preserves momentum conservation, or whether it actually eliminates the stress term that 'hinders the avatar's ability to achieve a desired pose.'
minor comments (1)
  1. The abstract refers to evaluation on human-object and human-human scenarios but supplies no quantitative metrics, baselines, or ablation results, preventing assessment of practical gains.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We respond to each major comment below, referring to the relevant sections of the full manuscript where the technical details appear. We will revise the abstract to incorporate key equations and brief descriptions for improved clarity.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the assertion that the skeletal framework 'allows estimating its poses and real-time tracking in a closed form, even during non-rigid physical interactions' is load-bearing for the central claim yet unsupported by any derivation, equation, or algorithmic description. Non-rigid MPM particle motion alters effective bone attachments, converting skeletal recovery into an inverse problem that normally requires optimization; without an explicit closed-form map that remains valid post-deformation, the ability to achieve desired poses under external forces cannot be verified.

    Authors: The manuscript (Section 4) derives the closed-form pose estimation by integrating the skeletal framework with the decoupled deformation gradient. The decoupling isolates the kinematic velocity component, so bone attachment transformations are computed solely from this component and remain unaffected by non-rigid particle motion; the explicit map is the rigid transformation matrix updated directly from the kinematic velocity field without requiring optimization. This holds post-deformation because the deformation gradient update excludes the kinematic contribution. We agree the abstract would be strengthened by referencing this derivation and will revise it to include a concise statement of the closed-form map. revision: yes

  2. Referee: [Abstract] Abstract: the key insight of decoupling kinematic velocity from deformation gradient is stated without accompanying equations or MPM update rules. It is therefore impossible to assess whether the decoupling is parameter-free, whether it preserves momentum conservation, or whether it actually eliminates the stress term that 'hinders the avatar's ability to achieve a desired pose.'

    Authors: Section 3.1 presents the MPM update rules with the explicit velocity decomposition: total velocity v = v_kin + v_def, where only v_def contributes to the deformation gradient F update via the standard MPM constitutive model, while v_kin is applied separately to particle positions without altering F. This decomposition is parameter-free, follows directly from additive velocity splitting, and preserves total momentum because the sum v remains unchanged. The stress term associated with kinematic motion is eliminated because F is unaffected by v_kin. We will revise the abstract to include the core equations for the decoupling and the resulting stress elimination. revision: yes

Circularity Check

0 steps flagged

No circularity; derivation introduces independent decoupling and skeletal integration without reduction to inputs.

full rationale

The paper's central claims rest on a proposed decoupling of kinematic velocity from deformation gradient plus integration of a skeletal framework stated to enable closed-form pose estimation under non-rigid MPM dynamics. No equations, fitted parameters, or self-citations are exhibited that reduce any prediction or result to the inputs by construction. The skeletal closed-form claim is presented as a direct consequence of the integration rather than a renamed fit or self-referential definition. The overall method is implemented inside a standard MPM framework and evaluated on interaction scenarios, keeping the derivation self-contained against external physical simulation benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No free parameters, axioms, or invented entities are specified in the abstract.

pith-pipeline@v0.9.1-grok · 5742 in / 1083 out tokens · 29161 ms · 2026-07-01T07:25:01.426662+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

79 extracted references · 4 canonical work pages · 1 internal anchor

  1. [1]

    In: ACM Transactions on Graphics (TOG)

    Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM Transactions on Graphics (TOG). ACM (2005)

    2005

  2. [2]

    Authors, G.: Genesis: A generative and universal physics engine for robotics and beyond (December 2024),https://github.com/Genesis-Embodied-AI/Genesis

    2024

  3. [3]

    Qwen2.5-VL Technical Report

    Bai, S., Chen, K., Liu, X., Wang, J., Ge, W., Song, S., Dang, K., Wang, P., Wang, S., Tang, J., Zhong, H., Zhu, Y., Yang, M., Li, Z., Wan, J., Wang, P., Ding, W., Fu, Z., Xu, Y., Ye, J., Zhang, X., Xie, T., Cheng, Z., Zhang, H., Yang, Z., Xu, H., Lin, J.: Qwen2.5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  4. [4]

    Computer Methods in Applied Mechanics and Engineering 187(3–4), 529–541 (2000)

    Bardenhagen, S.G., Brackbill, J.U., Sulsky, D.: The material-point method for granular materials. Computer Methods in Applied Mechanics and Engineering 187(3–4), 529–541 (2000)

    2000

  5. [5]

    In: Proceedings of European Conference on Computer Vision (ECCV) (2016)

    Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image. In: Proceedings of European Conference on Computer Vision (ECCV) (2016)

    2016

  6. [6]

    Clough,R.:TheFiniteElementMethodinPlaneStressAnalysis.AmericanSociety of Civil Engineers (1960),https://books.google.co.kr/books?id=rfwFHQAACAAJ

    1960

  7. [7]

    Corporation, N.: Nvidia physx sdk.https://developer.nvidia.com/physx-sdk (2021), accessed: March 2025

    2021

  8. [8]

    In: ACM SIGGRAPH 2015 Courses, p

    Coumans, E.: Bullet physics simulation. In: ACM SIGGRAPH 2015 Courses, p. 1. ACM (2015)

    2015

  9. [9]

    In: Recent advances in optimization and mod- eling of contemporary problems

    Frazier, P.I.: Bayesian optimization. In: Recent advances in optimization and mod- eling of contemporary problems. Informs (2018)

    2018

  10. [10]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    Guo, C., Jiang, T., Chen, X., Song, J., Hilliges, O.: Vid2avatar: 3d avatar re- construction from videos in the wild via self-supervised scene decomposition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    2023

  11. [11]

    ACM Transactions on Graphics (TOG) (2018)

    Guo, Q., Han, X., Fu, C., Gast, T., Tamstorf, R., Teran, J.: A material point method for thin shells with frictional contact. ACM Transactions on Graphics (TOG) (2018)

    2018

  12. [12]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    Han, S.H., Park, M.G., Yoon, J.H., Kang, J.M., Park, Y.J., Jeon, H.G.: High- fidelity 3d human digitization from single 2k resolution images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    2023

  13. [13]

    ACM Transactions on Graphics (TOG) (2019)

    Han, X., Gast, T.F., Guo, Q., Wang, S., Jiang, C., Teran, J.: A hybrid material point method for frictional contact with diverse materials. ACM Transactions on Graphics (TOG) (2019)

    2019

  14. [14]

    ACM Transactions on Programming Lan- guages and Systems (TOPLAS) (1991)

    Herlihy, M.: Wait-free synchronization. ACM Transactions on Programming Lan- guages and Systems (TOPLAS) (1991)

    1991

  15. [15]

    In: Proceedings of IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR) (2024) 24 S

    Ho, I., Song, J., Hilliges, O., et al.: Sith: Single-view textured human reconstruction with image-conditioned diffusion. In: Proceedings of IEEE Conference on Com- puter Vision and Pattern Recognition (CVPR) (2024) 24 S. Han et al

    2024

  16. [16]

    Proceedings of the Neural Information Processing Systems (NeurIPS) (2024)

    Hu, H., Fan, Z., Wu, T., Xi, Y., Lee, S., Pavlakos, G., Wang, Z., et al.: Expressive gaussian human avatars from monocular rgb video. Proceedings of the Neural Information Processing Systems (NeurIPS) (2024)

    2024

  17. [17]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Hu, L., Zhang, H., Zhang, Y., Zhou, B., Liu, B., Zhang, S., Nie, L.: Gaussianavatar: Towards realistic human avatar modeling from a single video via animatable 3d gaussians. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  18. [18]

    ACM Transactions on Graphics (TOG) (2018)

    Hu, Y., Fang, Y., Ge, Z., Qu, Z., Zhu, Y., Pradhana, A., Jiang, C.: A moving least squares material point method with displacement discontinuity and two-way rigid body coupling. ACM Transactions on Graphics (TOG) (2018)

    2018

  19. [19]

    ACM Transactions on Graphics (TOG) (2023).https://doi.org/10.1145/ 3592415,https://doi.org/10.1145/3592415

    Işık, M., Rünz, M., Georgopoulos, M., Khakhulin, T., Starck, J., Agapito, L., Nießner, M.: Humanrf: High-fidelity neural radiance fields for humans in mo- tion. ACM Transactions on Graphics (TOG) (2023).https://doi.org/10.1145/ 3592415,https://doi.org/10.1145/3592415

    work page doi:10.1145/3592415 2023

  20. [20]

    ACM Transactions on Graphics (TOG) (2017)

    Jiang, C., Gast, T., Teran, J.: Anisotropic elastoplasticity for cloth, knit and hair frictional contact. ACM Transactions on Graphics (TOG) (2017)

    2017

  21. [21]

    ACM Transactions on Graphics (TOG) (2015)

    Jiang, C., Schroeder, C., Selle, A., Teran, J., Stomakhin, A.: The affine particle- in-cell method. ACM Transactions on Graphics (TOG) (2015)

    2015

  22. [22]

    Journal of Computational Physics (JCP) (2017)

    Jiang, C., Schroeder, C., Teran, J.: An angular momentum conserving affine- particle-in-cell method. Journal of Computational Physics (JCP) (2017)

    2017

  23. [23]

    In: Acm siggraph 2016 courses

    Jiang, C., Schroeder, C., Teran, J., Stomakhin, A., Selle, A.: The material point method for simulating continuum materials. In: Acm siggraph 2016 courses. ACM Transactions on Graphics (TOG) (2016)

    2016

  24. [24]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    Jiang, T., Chen, X., Song, J., Hilliges, O.: Instantavatar: Learning avatars from monocular video in 60 seconds. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    2023

  25. [25]

    Founda- tions of Crystallography (1976)

    Kabsch, W.: A solution for the best rotation to relate two sets of vectors. Founda- tions of Crystallography (1976)

    1976

  26. [26]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)

    2018

  27. [27]

    ACM Transactions on Graphics (TOG) (2023)

    Keller, M., Werling, K., Shin, S., Delp, S., Pujades, S., Liu, C.K., Black, M.J.: From skin to skeleton: Towards biomechanically accurate 3d digital humans. ACM Transactions on Graphics (TOG) (2023)

    2023

  28. [28]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

    Keller, M., Zuffi, S., Black, M.J., Pujades, S.: Osso: Obtaining skeletal shape from outside. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

    2022

  29. [29]

    ACM Transactions on Graphics (TOG) (2023)

    Kerbl, B., Kopanas, G., Leimkühler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics (TOG) (2023)

    2023

  30. [30]

    ACM Transactions on Graph- ics (TOG) (2017)

    Kim, M., Pons-Moll, G., Pujades, S., Bang, S., Kim, J., Black, M.J., Lee, S.H.: Data-driven physics for human soft tissue animation. ACM Transactions on Graph- ics (TOG) (2017)

    2017

  31. [31]

    Klár, G., Gast, T., Pradhana, A., Fu, C., Schroeder, C., Jiang, C., Teran, J.: Drucker-pragerelastoplasticityforsandanimation.ACMTransactionsonGraphics (TOG) (2016)

    2016

  32. [32]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: Video inference for human body pose and shape estimation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    2020

  33. [33]

    In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2025) PIAvatar 25

    Lee, C., Lee, J., Kim, T.K.: Mpmavatar: Learning 3d gaussian avatars with accu- rate and robust physics-based dynamics. In: Proceedings of the Neural Information Processing Systems (NeurIPS) (2025) PIAvatar 25

    2025

  34. [34]

    ACM Transactions on Graphics (TOG) (2018)

    Lee, S., Yu, R., Park, J., Aanjaneya, M., Sifakis, E., Lee, J.: Dexterous manipula- tion and control with volumetric muscles. ACM Transactions on Graphics (TOG) (2018)

    2018

  35. [35]

    arXiv preprint arXiv:2012.04457 (2020) 22 S

    Li, M., Kaufman, D.M., Jiang, C.: Codimensional incremental potential contact. arXiv preprint arXiv:2012.04457 (2020)

    work page arXiv 2012

  36. [36]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Li, Z., Zheng, Z., Wang, L., Liu, Y.: Animatable gaussians: Learning pose- dependent gaussian maps for high-fidelity human avatar modeling. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  37. [37]

    ACM Transactions on Graphics (TOG) (2013)

    Liu, L., Yin, K., Wang, B., Guo, B.: Simulation and control of skeleton-driven soft body characters. ACM Transactions on Graphics (TOG) (2013)

    2013

  38. [38]

    ACM Transactions on Graphics (TOG) (2014)

    Loper, M., Mahmood, N., Black, M.J.: Mosh: motion and shape capture from sparse markers. ACM Transactions on Graphics (TOG) (2014)

    2014

  39. [39]

    ACM Transactions on Graphics (TOG) (2015)

    Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. ACM Transactions on Graphics (TOG) (2015)

    2015

  40. [40]

    In: Proceedings of International Conference on Computer Vision (ICCV) (2023)

    Luo, Z., Cao, J., Kitani, K., Xu, W., et al.: Perpetual humanoid control for real- time simulated avatars. In: Proceedings of International Conference on Computer Vision (ICCV) (2023)

    2023

  41. [41]

    International Confer- ence on Learning Representations (ICLR) (2023)

    Luo, Z., Cao, J., Merel, J., Winkler, A., Huang, J., Kitani, K., Xu, W.: Universal humanoid motion representations for physics-based control. International Confer- ence on Learning Representations (ICLR) (2023)

    2023

  42. [42]

    In: Proceedings of International Con- ference on Computer Vision (ICCV) (2019)

    Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: Amass: Archive of motion capture as surface shapes. In: Proceedings of International Con- ference on Computer Vision (ICCV) (2019)

    2019

  43. [43]

    maximeraafat: Blendernerf.https://github.com/maximeraafat/BlenderNeRF (2023)

    2023

  44. [44]

    ACM Transactions on Graphics (TOG) (2024)

    Moenne-Loccoz, N., Mirzaei, A., Perel, O., de Lutio, R., Esturo, J.M., State, G., Fidler, S., Sharp, N., Gojcic, Z.: 3d gaussian ray tracing: Fast tracing of particle scenes. ACM Transactions on Graphics (TOG) (2024)

    2024

  45. [45]

    In: Proceedings of European Conference on Computer Vision (ECCV) (2024)

    Moon, G., Shiratori, T., Saito, S.: Expressive whole-body 3d gaussian avatar. In: Proceedings of European Conference on Computer Vision (ECCV) (2024)

    2024

  46. [46]

    ACM transactions on graphics (TOG)24(3), 471–478 (2005)

    Müller,M.,Heidelberger,B.,Teschner,M.,Gross,M.:Meshlessdeformationsbased on shape matching. ACM transactions on graphics (TOG)24(3), 471–478 (2005)

    2005

  47. [47]

    Proceedings of the Neural Information Processing Systems (NeurIPS) (2024)

    Pan, P., Su, Z., Lin, C., Fan, Z., Zhang, Y., Li, Z., Shen, T., Mu, Y., Liu, Y.: Hu- mansplat: Generalizable single-image human gaussian splatting with structure pri- ors. Proceedings of the Neural Information Processing Systems (NeurIPS) (2024)

    2024

  48. [48]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A.A., Tzionas, D., Black, M.J.: Expressive body capture: 3D hands, face, and body from a sin- gle image. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    2019

  49. [49]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., Black,M.J.:Expressivebodycapture:3dhands,face,andbodyfromasingleimage. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)

    2019

  50. [50]

    In: Proceedings of International Conference on Computer Vision (ICCV) (2021)

    Peng, S., Dong, J., Wang, Q., Zhang, S., Shuai, Q., Zhou, X., Bao, H.: Animatable neural radiance fields for modeling dynamic human bodies. In: Proceedings of International Conference on Computer Vision (ICCV) (2021)

    2021

  51. [51]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021) 26 S

    Peng, S., Zhang, Y., Xu, Y., Wang, Q., Shuai, Q., Bao, H., Zhou, X.: Neural body: Implicit neural representations with structured latent codes for novel view synthesis of dynamic humans. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021) 26 S. Han et al

    2021

  52. [52]

    ACM Transactions on Graphics (TOG) (2018)

    Peng, X.B., Abbeel, P., Levine, S., van de Panne, M.: Deepmimic: Example-guided deep reinforcement learning of physics-based character skills. ACM Transactions on Graphics (TOG) (2018)

    2018

  53. [53]

    ACM Transactions on Graphics (TOG) (2021)

    Peng, X.B., Ma, Z., Abbeel, P., Levine, S., Kanazawa, A.: Amp: Adversarial motion priors for stylized physics-based character control. ACM Transactions on Graphics (TOG) (2021)

    2021

  54. [54]

    Proceedings of International Conference on Computer Vision (ICCV) (2025)

    Qiu, L., Gu, X., Li, P., Zuo, Q., Shen, W., Zhang, J., Qiu, K., Yuan, W., Chen, G., Dong, Z., et al.: Lhm: Large animatable human reconstruction model from a single image in seconds. Proceedings of International Conference on Computer Vision (ICCV) (2025)

    2025

  55. [55]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    Qiu, L., Zhu, S., Zuo, Q., Gu, X., Dong, Y., Zhang, J., Xu, C., Li, Z., Yuan, W., Bo, L., et al.: Anigs: Animatable gaussian avatar from a single image with inconsistent gaussian reconstruction. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    2025

  56. [56]

    In: Proceedings of International Conference on Computer Vision (ICCV) (2019)

    Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of International Conference on Computer Vision (ICCV) (2019)

    2019

  57. [57]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Saito, S., Simon, T., Saragih, J., Joo, H.: Pifuhd: Multi-level pixel-aligned im- plicit function for high-resolution 3d human digitization. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    2020

  58. [58]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Shao, Z., Wang, Z., Li, Z., Wang, D., Lin, X., Zhang, Y., Fan, M., Wang, Z.: Splattingavatar: Realistic real-time human avatars with mesh-embedded gaussian splatting. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  59. [59]

    In: Pro- ceedings of European Conference on Computer Vision (ECCV) (2024)

    Shin, J., Lee, J., Lee, S., Park, M.G., Kang, J.M., Yoon, J.H., Jeon, H.G.: Canon- icalfusion: Generating drivable 3d human avatars from multiple images. In: Pro- ceedings of European Conference on Computer Vision (ECCV) (2024)

    2024

  60. [60]

    In: Proceedings of International Conference on Computer Vision (ICCV) (2025)

    Sim, G., Moon, G.: Persona: Personalized whole-body 3d avatar with pose-driven deformations from a single image. In: Proceedings of International Conference on Computer Vision (ICCV) (2025)

    2025

  61. [61]

    arXiv preprint arXiv:2507.23778 (2025)

    Siyao, L., Feng, Y., Taheri, O., Loy, C.C., Black, M.J.: Half-physics: Enabling kine- matic 3d human model with physical interactions. arXiv preprint arXiv:2507.23778 (2025)

    work page arXiv 2025

  62. [62]

    ACM Transactions on Graphics (TOG) (2013)

    Stomakhin, A., Schroeder, C., Chai, L., Teran, J., Selle, A.: A material point method for snow simulation. ACM Transactions on Graphics (TOG) (2013)

    2013

  63. [63]

    Proceedings of the Neural Information Processing Systems (NeurIPS) (2021)

    Su, S.Y., Yu, F., Zollhöfer, M., Rhodin, H.: A-nerf: Articulated neural radiance fields for learning human shape, appearance, and pose. Proceedings of the Neural Information Processing Systems (NeurIPS) (2021)

    2021

  64. [64]

    Tevet, G., Raab, S., Cohan, S., Reda, D., Luo, Z., Peng, X.B., Bermano, A.H., van de Panne, M.: Closd: Closing the loop between simulation and diffusion for multi-taskcharactercontrol.InternationalConferenceonLearningRepresentations (ICLR) (2025)

    2025

  65. [65]

    In: Proceedings of International Conference on Intelligent Robots and Systems (IROS)

    Todorov, E., Erez, T., Tassa, Y.: Mujoco: A physics engine for model-based control. In: Proceedings of International Conference on Intelligent Robots and Systems (IROS). IEEE (2012)

    2012

  66. [66]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025) PIAvatar 27

    Wang, R., Prada, F., Wang, Z., Jiang, Z., Yin, C., Li, J., Saito, S., Santesteban, I., Romero, J., Joshi, R., et al.: Fresa: Feedforward reconstruction of personalized skinned avatars from few images. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025) PIAvatar 27

    2025

  67. [67]

    In: Proceed- ings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Wen, J., Zhao, X., Ren, Z., Schwing, A.G., Wang, S.: Gomavatar: Efficient animat- able human modeling from monocular video using gaussians-on-mesh. In: Proceed- ings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  68. [68]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

    Weng, C.Y., Curless, B., Srinivasan, P.P., Barron, J.T., Kemelmacher-Shlizerman, I.: Humannerf: Free-viewpoint rendering of moving people from monocular video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)

    2022

  69. [69]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., Wang, X.: 4d gaussian splatting for real-time dynamic scene rendering. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  70. [70]

    Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    Wu, Q., Martinez Esturo, J., Mirzaei, A., Moenne-Loccoz, N., Gojcic, Z.: 3dgut: Enabling distorted cameras and secondary rays in gaussian splatting. Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    2025

  71. [71]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    Xie, T., Zong, Z., Qiu, Y., Li, X., Feng, Y., Yang, Y., Jiang, C.: Physgaussian: Physics-integrated 3d gaussians for generative dynamics. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2024)

    2024

  72. [72]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    Xiu, Y., Yang, J., Cao, X., Tzionas, D., Black, M.J.: Econ: Explicit clothed hu- mans optimized via normal integration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)

    2023

  73. [73]

    In: Proceedings of IEEE Conference on Computer Vision and Pat- tern Recognition (CVPR) (2022)

    Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: Icon: Implicit clothed humans obtained from normals. In: Proceedings of IEEE Conference on Computer Vision and Pat- tern Recognition (CVPR) (2022)

    2022

  74. [74]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Ghum & ghuml: Generative 3d human shape and articulated pose models. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)

    2020

  75. [75]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    Xu, S., Ling, H.Y., Wang, Y.X., Gui, L.Y.: Intermimic: Towards universal whole- body control for physics-based human-object interactions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    2025

  76. [76]

    Proceedings of the Neural Information Processing Systems (NeurIPS) (2024)

    Xue, Y., Xie, X., Marin, R., Pons-Moll, G.: Human 3diffusion: Realistic avatar creation via explicit 3d consistent diffusion models. Proceedings of the Neural Information Processing Systems (NeurIPS) (2024)

    2024

  77. [77]

    In: Proceedings of European Conference on Computer Vision (ECCV) (2024)

    Zheng, Y., Zhao, Q., Yang, G., Yifan, W., Xiang, D., Dubost, F., Lagun, D., Beeler, T., Tombari, F., Guibas, L., et al.: Physavatar: Learning the physics of dressed 3d avatars from visual observations. In: Proceedings of European Conference on Computer Vision (ECCV) (2024)

    2024

  78. [78]

    IEEE Transactions on Pat- tern Analysis and Machine Intelligence (PAMI) (2021)

    Zheng, Z., Yu, T., Liu, Y., Dai, Q.: Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction. IEEE Transactions on Pat- tern Analysis and Machine Intelligence (PAMI) (2021)

    2021

  79. [79]

    In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    Zhuang, Y., Lv, J., Wen, H., Shuai, Q., Zeng, A., Zhu, H., Chen, S., Yang, Y., Cao, X., Liu, W.: Idol: Instant photorealistic 3d human creation from a single image. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2025)

    2025