pith. sign in

arxiv: 2607.02034 · v1 · pith:O2F6OJXFnew · submitted 2026-07-02 · 💻 cs.CV

ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments

Lu Pan , Hongwei Zhao This is my paper

Pith reviewed 2026-07-03 16:04 UTC · model grok-4.3

classification 💻 cs.CV
keywords human-scene interactionphysics-based imitationmotion capture datacomplex 3D environmentsdual expert strategydifficulty-aware distillationcollision avoidanceembodied intelligence
0
0 comments X

The pith

A dual-expert framework with difficulty-aware distillation reconstructs diverse human-scene interactions from imperfect motion data in complex 3D environments.

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

The paper sets out to demonstrate that physics-based imitation of human interactions with scenes can succeed in cluttered, realistic 3D spaces by recovering useful signal from noisy motion-capture recordings. It notes an inherent tension between following captured motion closely and producing collision-free, physically stable behavior. The solution trains one expert focused on motion fidelity and another focused on scene adaptation, then combines them through a distillation process that gives more weight to difficult trajectories according to observed failures and learning progress. A sympathetic reader would care because prior methods have been limited to simplified rooms or single objects, so extending reliable imitation to everyday environments would make embodied agents far more practical. If the claim holds, the approach would allow training on existing imperfect datasets without per-scene redesign.

Core claim

The authors claim that ComplexMimic reconstructs diverse human-scene interactions in complex environments by interpreting imperfect MoCap data through a Dual Flow Strategy that maintains an imitation expert for accurate motion tracking alongside an interaction expert for collision-aware adaptation, followed by difficulty-aware distillation that adaptively weights supervision toward hard-yet-learnable trajectories using failure statistics and learning progress signals; this combination outperforms prior state-of-the-art methods across three benchmark datasets.

What carries the argument

Dual Flow Strategy consisting of an imitation expert and an interaction expert, combined via difficulty-aware distillation that prioritizes challenging behaviors.

If this is right

  • Imitation learning becomes feasible in cluttered rather than simplified scenes without extra scene-specific engineering.
  • Training can leverage existing imperfect MoCap datasets more effectively than uniform multi-expert distillation.
  • The resulting policies produce both higher motion accuracy and better physical plausibility on standard benchmarks.
  • Embodied agents gain access to a wider range of natural interaction behaviors in realistic 3D settings.

Where Pith is reading between the lines

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

  • The same separation of tracking and adaptation experts might transfer to other imitation domains that face noisy demonstration data, such as robot manipulation.
  • If the distillation weighting proves stable, it could reduce the need for manual curriculum design when scaling to larger scene collections.
  • Success here suggests that explicit difficulty signals from failure counts could be tested as a general regularizer in multi-task physics simulation.
  • Deployment in real robots would still require checking whether the learned collision avoidance survives sim-to-real gaps not addressed in the benchmarks.

Load-bearing premise

Imperfect motion-capture recordings contain enough recoverable information to support both precise motion tracking and collision-aware physical adaptation at the same time in complex scenes.

What would settle it

Running the method on a held-out collection of complex scenes with deliberately degraded MoCap data and finding that it produces either unnatural motions or frequent collisions while matching or falling below baseline performance.

Figures

Figures reproduced from arXiv: 2607.02034 by Hongwei Zhao, Lu Pan.

Figure 1
Figure 1. Figure 1: (a) Prior humanoid imitation-learning studies [20] typically focus on scene￾free or overly simplified environments (upper row), whereas our work targets realistic HSI imitation in complex 3D scenes (lower row). (b) Feasibility–faithfulness trade-off in HSI imitation. Varying the early termination threshold τ during training reveals a clear trade-off: larger τ improves task feasibility (higher success rate)… view at source ↗
Figure 2
Figure 2. Figure 2: Overview of ComplexMimic, a two-stage framework for human–scene inter￾action imitation in complex environments. In Stage I, an imitation expert and an interaction expert are trained to achieve motion-faithful tracking and collision-aware adaptation, respectively. In Stage II, these experts are frozen and distilled into a unified policy via Difficulty-Aware Distillation (DAD). Black arrows denote policy upd… view at source ↗
Figure 3
Figure 3. Figure 3: Examples of return improvement under different motion cases. The first refer￾ence motion conflicts heavily with the scene meshes, resulting in limited return gains. In contrast, the second motion achieves better tracking performance and larger return gains, demonstrating the effectiveness of our learning progress signal. A simple and effective choice is to set sk(m) proportional to the motion difficulty, s… view at source ↗
Figure 4
Figure 4. Figure 4: Qualitative comparisons on the TRUMANS [16] dataset. Red boxes highlight typical failure modes under complicated scenes, such as undesired collisions, unstable contacts, and noticeable deviations from the reference. More visual results can be found in the supplementary material. 4.4 Ablation Study Effectiveness of Dual Flow Strategy. As shown in Tab. 4, removing either teacher degrades the performance sign… view at source ↗
Figure 5
Figure 5. Figure 5: Qualitative ablation comparisons on TRUMANS [16]. showing that (i) focusing updates on harder motions within each regime and (ii) balancing training across regimes are both beneficial. The learnability filtering is particularly important: removing it significantly degrades both Succ (from 0.906 to 0.877) and Eg-mpjpe (from 77.840 to 88.497), suggesting that suppressing hard but unlearnable clips is necessa… view at source ↗
Figure 6
Figure 6. Figure 6: Visualization of our method in Isaac Lab [PITH_FULL_IMAGE:figures/full_fig_p024_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Visualization under different body scales. J Discussion Limitations and Future Work. Although our method demonstrates strong performance on human–scene interaction imitation under complex 3D environ￾ments, it still has several limitations. First, our method cannot handle cases where the reference motion severely penetrates the scene meshes, as illustrated [PITH_FULL_IMAGE:figures/full_fig_p024_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Examples of failure cases. The reference motion is severely penetrated with the 3D environments. in [PITH_FULL_IMAGE:figures/full_fig_p025_8.png] view at source ↗
read the original abstract

Physics-based Human-Scene Interaction (HSI) imitation learning is crucial for embodied intelligence as it bridges the gap between kinematic 3D motions and real-world dynamics. However, most existing methods focus on simplified scene settings, leaving complex environments largely unexplored, which limits their applicability in real-world scenarios. In this paper, we focus on HSI mimicry in complex environments. Under this complex setting, we observe an inherent trade-off between successfully performing interaction and maintaining natural, physically plausible motions. To address this challenge, we propose ComplexMimic, a framework that reconstructs diverse HSI by interpreting imperfect MoCap data. First, we introduce a Dual Flow Strategy, which learns two complementary experts: an imitation expert for accurate motion tracking and an interaction expert for collision-aware adaptation in complex scenes. Second, naive multi-expert distillation, which treats all experts equally, often under-samples challenging behaviors, limiting effective learning. To mitigate this issue, we propose a difficulty-aware distillation strategy that adaptively weights supervision and prioritizes hard-yet-learnable trajectories guided by failure statistics and learning progress signals. Extensive experiments on three benchmark datasets demonstrate that our approach outperforms current state-of-the-art methods. Our implementation is available at https://github.com/LuPan23/ComplexMimic.

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

1 major / 0 minor

Summary. The paper proposes ComplexMimic, a framework for physics-based human-scene interaction (HSI) imitation learning in complex 3D environments. It introduces a Dual Flow Strategy consisting of an imitation expert for motion tracking and an interaction expert for collision-aware adaptation, together with a difficulty-aware distillation method that weights supervision based on failure statistics and learning progress. The central claim is that this approach reconstructs diverse HSI from imperfect MoCap data and outperforms current state-of-the-art methods on three benchmark datasets.

Significance. If the empirical claims of outperformance hold with rigorous quantitative support, the work would address an important gap in handling complex scenes for embodied HSI, moving beyond simplified settings. The dual-expert and adaptive-distillation ideas are conceptually plausible for managing the noted trade-off between interaction success and motion plausibility. However, the provided text supplies no metrics, ablations, or dataset details, so significance cannot be assessed.

major comments (1)
  1. [Abstract] Abstract: The assertion that the method 'outperforms current state-of-the-art methods' on three benchmark datasets is unsupported by any quantitative metrics, ablation results, error bars, dataset descriptions, or implementation details. This absence makes the central empirical claim unverifiable from the manuscript.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and the opportunity to clarify our manuscript. We address the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion that the method 'outperforms current state-of-the-art methods' on three benchmark datasets is unsupported by any quantitative metrics, ablation results, error bars, dataset descriptions, or implementation details. This absence makes the central empirical claim unverifiable from the manuscript.

    Authors: We agree that the abstract would benefit from explicit quantitative support to make the central claim immediately verifiable. The full manuscript contains these elements in the Experiments section (including performance tables on three benchmarks, ablation studies, error analysis, dataset details, and implementation information). We will revise the abstract to incorporate key quantitative highlights from those results. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The abstract and available description present an empirical framework (Dual Flow Strategy with imitation and interaction experts, plus difficulty-aware distillation) whose central claims rest on outperformance across three external benchmark datasets. No equations, parameter-fitting steps, self-citations, or uniqueness theorems are referenced that would allow any result to reduce to its own inputs by construction. The derivation chain is therefore self-contained against external benchmarks and receives the default non-circularity finding.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no free parameters, axioms, or invented entities are described in sufficient detail to populate the ledger.

pith-pipeline@v0.9.1-grok · 5753 in / 1034 out tokens · 25631 ms · 2026-07-03T16:04:47.737495+00:00 · methodology

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

53 extracted references · 16 canonical work pages · 9 internal anchors

  1. [1]

    In: Proceed- ings of the IEEE/CVF International Conference on Computer Vision

    Collorone, L., Gioia, M., Pappa, M., Leoni, P., Ficarra, G., Litany, O., Spinelli, I., Galasso, F.: Monster: a unified model for motion, scene, text retrieval. In: Proceed- ings of the IEEE/CVF International Conference on Computer Vision. pp. 10940– 10949 (2025)

    2025

  2. [2]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: Generating di- verse and natural 3d human motions from text. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 5152–5161 (2022)

    2022

  3. [3]

    In: European Conference on Computer Vision

    Guo, C., Zuo, X., Wang, S., Cheng, L.: Tm2t: Stochastic and tokenized model- ing for the reciprocal generation of 3d human motions and texts. In: European Conference on Computer Vision. pp. 580–597. Springer (2022)

    2022

  4. [4]

    In: Proceedings of the IEEE/CVF In- ternational Conference on Computer Vision

    Hassan, M., Ceylan, D., Villegas, R., Saito, J., Yang, J., Zhou, Y., Black, M.J.: Stochastic scene-aware motion prediction. In: Proceedings of the IEEE/CVF In- ternational Conference on Computer Vision. pp. 11374–11384 (2021)

    2021

  5. [5]

    In: Proceedings of the IEEE/CVF international conference on computer vision

    Hassan, M., Choutas, V., Tzionas, D., Black, M.J.: Resolving 3d human pose ambi- guities with 3d scene constraints. In: Proceedings of the IEEE/CVF international conference on computer vision. pp. 2282–2292 (2019)

    2019

  6. [6]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3d scenes by learning human-scene interaction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 14708–14718 (2021)

    2021

  7. [7]

    In: ACM SIGGRAPH 2023 Conference Pro- ceedings

    Hassan, M., Guo, Y., Wang, T., Black, M., Fidler, S., Peng, X.B.: Synthesizing physical character-scene interactions. In: ACM SIGGRAPH 2023 Conference Pro- ceedings. pp. 1–9 (2023)

    2023

  8. [8]

    arXiv preprint arXiv:2502.01143 (2025)

    He, T., Gao, J., Xiao, W., Zhang, Y., Wang, Z., Wang, J., Luo, Z., He, G., Soban- bab, N., Pan, C., et al.: Asap: Aligning simulation and real-world physics for learn- ing agile humanoid whole-body skills. arXiv preprint arXiv:2502.01143 (2025)

    work page arXiv 2025

  9. [9]

    Omnih2o: Universal and dexterous human- to-humanoid whole-body teleoperation and learning,

    He,T.,Luo,Z.,He,X.,Xiao,W.,Zhang,C.,Zhang,W.,Kitani,K.,Liu,C.,Shi,G.: Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning. arXiv preprint arXiv:2406.08858 (2024)

    work page arXiv 2024

  10. [10]

    Distilling the Knowledge in a Neural Network

    Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015) 16 L. Pan and H. Zhao

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  11. [11]

    Advances in neural information processing systems33, 6840–6851 (2020)

    Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Advances in neural information processing systems33, 6840–6851 (2020)

    2020

  12. [12]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Huang, C.H.P., Yi, H., Höschle, M., Safroshkin, M., Alexiadis, T., Polikovsky, S., Scharstein, D., Black, M.J.: Capturing and inferring dense full-body human-scene contact. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 13274–13285 (2022)

    2022

  13. [13]

    In: Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision

    Hwang,I.,Zhou,B.,Kim,Y.M.,Wang,J.,Guo,C.:Scenemi:Motionin-betweening for modeling human-scene interaction. In: Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision. pp. 6034–6045 (2025)

    2025

  14. [14]

    Neural computation3(1), 79–87 (1991)

    Jacobs, R.A., Jordan, M.I., Nowlan, S.J., Hinton, G.E.: Adaptive mixtures of local experts. Neural computation3(1), 79–87 (1991)

    1991

  15. [15]

    In: SIGGRAPH Asia 2024 Conference Papers

    Jiang, N., He, Z., Wang, Z., Li, H., Chen, Y., Huang, S., Zhu, Y.: Autonomous character-scene interaction synthesis from text instruction. In: SIGGRAPH Asia 2024 Conference Papers. pp. 1–11 (2024)

    2024

  16. [16]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Jiang, N., Zhang, Z., Li, H., Ma, X., Wang, Z., Chen, Y., Liu, T., Zhu, Y., Huang, S.: Scaling up dynamic human-scene interaction modeling. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 1737– 1747 (2024)

    2024

  17. [17]

    Adam: A Method for Stochastic Optimization

    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  18. [18]

    BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion

    Liao, Q., Truong, T.E., Huang, X., Gao, Y., Tevet, G., Sreenath, K., Liu, C.K.: Beyondmimic: From motion tracking to versatile humanoid control via guided dif- fusion. arXiv preprint arXiv:2508.08241 (2025)

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  19. [19]

    In: European Conference on Computer Vision

    Liu, X., Hou, H., Yang, Y., Li, Y.L., Lu, C.: Revisit human-scene interaction via space occupancy. In: European Conference on Computer Vision. pp. 1–19. Springer (2024)

    2024

  20. [20]

    arXiv preprint arXiv:2412.17730 (2024)

    Liu, Y., Yang, B., Zhong, L., Wang, H., Yi, L.: Mimicking-bench: A benchmark for generalizable humanoid-scene interaction learning via human mimicking. arXiv preprint arXiv:2412.17730 (2024)

    work page arXiv 2024

  21. [21]

    Liu, Z., Ge, J., Xiong, M., Gu, J., Tang, B., Jing, W., Chen, S.: It takes two: Learning interactive whole-body control between humanoid robots (2025)

    2025

  22. [22]

    Luo, Z., Cao, J., Kitani, K., Xu, W., et al.: Perpetual humanoid control for real- timesimulatedavatars.In:ProceedingsoftheIEEE/CVFInternationalConference on Computer Vision. pp. 10895–10904 (2023)

    2023

  23. [23]

    Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

    Makoviychuk, V., Wawrzyniak, L., Guo, Y., Lu, M., Storey, K., Macklin, M., Hoeller, D., Rudin, N., Allshire, A., Handa, A., et al.: Isaac gym: High performance gpu-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021)

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  24. [24]

    In: 2024 International Conference on 3D Vision (3DV)

    Pan, L., Wang, J., Huang, B., Zhang, J., Wang, H., Tang, X., Wang, Y.: Syn- thesizing physically plausible human motions in 3d scenes. In: 2024 International Conference on 3D Vision (3DV). pp. 1498–1507. IEEE (2024)

    2024

  25. [25]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Pan, L., Yang, Z., Dou, Z., Wang, W., Huang, B., Dai, B., Komura, T., Wang, J.: Tokenhsi: Unified synthesis of physical human-scene interactions through task tokenization. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 5379–5391 (2025)

    2025

  26. [26]

    In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., Black, M.J.: Expressive body capture: 3d hands, face, and body from a single im- age. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 10975–10985 (2019) ComplexMimic 17

    2019

  27. [27]

    ACM Transactions On Graphics (TOG)37(4), 1–14 (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)37(4), 1–14 (2018)

    2018

  28. [28]

    Peng, X.B., Guo, Y., Halper, L., Levine, S., Fidler, S.: Ase: Large-scale reusable adversarialskillembeddingsforphysicallysimulatedcharacters.ACMTransactions On Graphics (TOG)41(4), 1–17 (2022)

    2022

  29. [29]

    ACM Transactions on Graphics (ToG)40(4), 1–20 (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)40(4), 1–20 (2021)

    2021

  30. [30]

    High-Dimensional Continuous Control Using Generalized Advantage Estimation

    Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  31. [31]

    Proximal Policy Optimization Algorithms

    Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  32. [32]

    arXiv preprint arXiv:2508.07842 (2025)

    Shen, Y., Liu, H., Zhang, L., Liu, P., Xia, R., Yao, T., Feng, T.: Detach: Cross- domain learning for long-horizon tasks via mixture of disentangled experts. arXiv preprint arXiv:2508.07842 (2025)

    work page arXiv 2025

  33. [33]

    In: nternational conference on machine learning

    Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsuper- vised learning using nonequilibrium thermodynamics. In: nternational conference on machine learning. pp. 2256–2265 (2015)

    2015

  34. [34]

    Denoising Diffusion Implicit Models

    Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)

    work page internal anchor Pith review Pith/arXiv arXiv 2010

  35. [35]

    Score-Based Generative Modeling through Stochastic Differential Equations

    Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score- based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)

    work page internal anchor Pith review Pith/arXiv arXiv 2011

  36. [36]

    ACM Trans- actions On Graphics (TOG)43(6), 1–21 (2024)

    Tessler, C., Guo, Y., Nabati, O., Chechik, G., Peng, X.B.: Maskedmimic: Unified physics-based character control through masked motion inpainting. ACM Trans- actions On Graphics (TOG)43(6), 1–21 (2024)

    2024

  37. [37]

    Human Motion Diffusion Model

    Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  38. [38]

    In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision

    Wang, W., Pan, L., Dou, Z., Mei, J., Liao, Z., Lou, Y., Wu, Y., Yang, L., Wang, J., Komura, T.: Sims: Simulating stylized human-scene interactions with retrieval- augmented script generation. In: Proceedings of the IEEE/CVF International Con- ference on Computer Vision. pp. 14117–14127 (2025)

    2025

  39. [39]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wang, Y., Zhao, Q., Yu, R., Tsui, H.W., Zeng, A., Lin, J., Luo, Z., Yu, J., Li, X., Chen, Q., et al.: Skillmimic: Learning basketball interaction skills from demon- strations. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 17540–17549 (2025)

    2025

  40. [40]

    arXiv preprint arXiv:2506.12779 (2025)

    Wang, Y., Yang, M., Ding, Z., Zhang, Y., Zeng, W., Xu, X., Jiang, H., Lu, Z.: From experts to a generalist: Toward general whole-body control for humanoid robots. arXiv preprint arXiv:2506.12779 (2025)

    work page arXiv 2025

  41. [41]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Wang,Z.,Chen,Y.,Jia,B.,Li,P.,Zhang,J.,Zhang,J.,Liu,T.,Zhu,Y.,Liang,W., Huang, S.: Move as you say interact as you can: Language-guided human motion generation with scene affordance. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 433–444 (2024)

    2024

  42. [42]

    Advances in Neural Informa- tion Processing Systems35, 14959–14971 (2022)

    Wang, Z., Chen, Y., Liu, T., Zhu, Y., Liang, W., Huang, S.: Humanise: Language- conditioned human motion generation in 3d scenes. Advances in Neural Informa- tion Processing Systems35, 14959–14971 (2022)

    2022

  43. [43]

    arXiv preprint arXiv:2309.07918 (2023) 18 L

    Xiao, Z., Wang, T., Wang, J., Cao, J., Zhang, W., Dai, B., Lin, D., Pang, J.: Unified human-scene interaction via prompted chain-of-contacts. arXiv preprint arXiv:2309.07918 (2023) 18 L. Pan and H. Zhao

    work page arXiv 2023

  44. [44]

    ACM Transactions on Graphics (TOG)44(6), 1–14 (2025)

    Xu, P., Wu, Z., Wang, R., Sarukkai, V., Fatahalian, K., Karamouzas, I., Zordan, V., Liu, C.K.: Learning to ball: Composing policies for long-horizon basketball moves. ACM Transactions on Graphics (TOG)44(6), 1–14 (2025)

    2025

  45. [45]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    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 the Computer Vision and Pattern Recognition Conference. pp. 12266–12277 (2025)

    2025

  46. [46]

    In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers

    Yu,R.,Wang,Y.,Zhao,Q.,Tsui,H.W.,Wang,J.,Tan,P.,Chen,Q.:Skillmimic-v2: Learning robust and generalizable interaction skills from sparse and noisy demon- strations. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers. pp. 1–11 (2025)

    2025

  47. [47]

    In: Proceedings of the Computer Vision and Pattern Recognition Conference

    Zhang, J., Fan, H., Yang, Y.: Energymogen: Compositional human motion gen- eration with energy-based diffusion model in latent space. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 17592–17602 (2025)

    2025

  48. [48]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

    Zhang, J., Fan, H., Yang, Y.: Towards decompositional human motion generation with energy-based diffusion models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. pp. 30650–30660 (2026)

    2026

  49. [49]

    In: Proceedings of theIEEE/CVF conference on computer vision and pattern recognition

    Zhang, J., Zhang, Y., Cun, X., Zhang, Y., Zhao, H., Lu, H., Shen, X., Shan, Y.: Generating human motion from textual descriptions with discrete representa- tions. In: Proceedings of theIEEE/CVF conference on computer vision and pattern recognition. pp. 14730–14740 (2023)

    2023

  50. [50]

    IEEE transactions on pattern analysis and machine intelligence46(6), 4115–4128 (2024)

    Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., Liu, Z.: Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE transactions on pattern analysis and machine intelligence46(6), 4115–4128 (2024)

    2024

  51. [51]

    In: European Conference on Computer Vision (ECCV) (2022)

    Zhao, K., Wang, S., Zhang, Y., Beeler, T., Tang, S.: Compositional human-scene interaction synthesis with semantic control. In: European Conference on Computer Vision (ECCV) (2022)

    2022

  52. [52]

    In: Proceedings of the IEEE/CVF international con- ference on computer vision

    Zhao, K., Zhang, Y., Wang, S., Beeler, T., Tang, S.: Synthesizing diverse human motions in 3d indoor scenes. In: Proceedings of the IEEE/CVF international con- ference on computer vision. pp. 14738–14749 (2023)

    2023

  53. [53]

    w/o” indicates removal; “–

    Zheng, Y., Yang, Y., Mo, K., Li, J., Yu, T., Liu, Y., Liu, C.K., Guibas, L.J.: Gimo: Gaze-informed human motion prediction in context. In: European Conference on Computer Vision. pp. 676–694. Springer (2022) ComplexMimic 19 Supplementary Material In this supplementary material, we present: –Sec. A: Additional ablation results on LINGO [15] and GIMO [53]. ...

    work page arXiv 2022