{"ID":5675311,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02034","arxiv_id":"2607.02034","title":"ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments","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.","short_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 applicabi...","url_abs":"https://arxiv.org/abs/2607.02034","url_pdf":"https://arxiv.org/pdf/2607.02034v1","authors":"[\"Lu Pan\",\"Hongwei Zhao\"]","published":"2026-07-02T11:01:20Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":613897,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-03T01:40:09.565152011Z","DeletedAt":null,"paper_id":5675311,"paper_url":"https://arxiv.org/abs/2607.02034","paper_title":"ComplexMimic: Human-Scene Interaction Imitation in Complex 3D Environments","repo_url":"https://github.com/LuPan23/ComplexMimic","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}