Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917072918806528 |
|---|---|
| author | Jingyu, Gong Kunkun, Tong Zhuoran, Chen Chuanhan, Yuan Mingang, Chen Zhizhong, Zhang Xin, Tan Yuan, Xie |
| author_facet | Jingyu, Gong Kunkun, Tong Zhuoran, Chen Chuanhan, Yuan Mingang, Chen Zhizhong, Zhang Xin, Tan Yuan, Xie |
| contents | Human motion synthesis in 3D scenes relies heavily on scene comprehension, while current methods focus mainly on scene structure but ignore the semantic understanding. In this paper, we propose a human motion synthesis framework that take an unified Scene Semantic Occupancy (SSO) for scene representation, termed SSOMotion. We design a bi-directional tri-plane decomposition to derive a compact version of the SSO, and scene semantics are mapped to an unified feature space via CLIP encoding and shared linear dimensionality reduction. Such strategy can derive the fine-grained scene semantic structures while significantly reduce redundant computations. We further take these scene hints and movement direction derived from instructions for motion control via frame-wise scene query. Extensive experiments and ablation studies conducted on cluttered scenes using ShapeNet furniture, as well as scanned scenes from PROX and Replica datasets, demonstrate its cutting-edge performance while validating its effectiveness and generalization ability. Code will be publicly available at https://github.com/jingyugong/SSOMotion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_07819 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy Jingyu, Gong Kunkun, Tong Zhuoran, Chen Chuanhan, Yuan Mingang, Chen Zhizhong, Zhang Xin, Tan Yuan, Xie Computer Vision and Pattern Recognition Human motion synthesis in 3D scenes relies heavily on scene comprehension, while current methods focus mainly on scene structure but ignore the semantic understanding. In this paper, we propose a human motion synthesis framework that take an unified Scene Semantic Occupancy (SSO) for scene representation, termed SSOMotion. We design a bi-directional tri-plane decomposition to derive a compact version of the SSO, and scene semantics are mapped to an unified feature space via CLIP encoding and shared linear dimensionality reduction. Such strategy can derive the fine-grained scene semantic structures while significantly reduce redundant computations. We further take these scene hints and movement direction derived from instructions for motion control via frame-wise scene query. Extensive experiments and ablation studies conducted on cluttered scenes using ShapeNet furniture, as well as scanned scenes from PROX and Replica datasets, demonstrate its cutting-edge performance while validating its effectiveness and generalization ability. Code will be publicly available at https://github.com/jingyugong/SSOMotion. |
| title | Human Motion Synthesis in 3D Scenes via Unified Scene Semantic Occupancy |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.07819 |