Proactive Scene Decomposition and Reconstruction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912657259364352 |
|---|---|
| author | Li, Baicheng Yan, Zike Wu, Dong Zha, Hongbin |
| author_facet | Li, Baicheng Yan, Zike Wu, Dong Zha, Hongbin |
| contents | Human behaviors are the major causes of scene dynamics and inherently contain rich cues regarding the dynamics. This paper formalizes a new task of proactive scene decomposition and reconstruction, an online approach that leverages human-object interactions to iteratively disassemble and reconstruct the environment. By observing these intentional interactions, we can dynamically refine the decomposition and reconstruction process, addressing inherent ambiguities in static object-level reconstruction. The proposed system effectively integrates multiple tasks in dynamic environments such as accurate camera and object pose estimation, instance decomposition, and online map updating, capitalizing on cues from human-object interactions in egocentric live streams for a flexible, progressive alternative to conventional object-level reconstruction methods. Aided by the Gaussian splatting technique, accurate and consistent dynamic scene modeling is achieved with photorealistic and efficient rendering. The efficacy is validated in multiple real-world scenarios with promising advantages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_16272 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Proactive Scene Decomposition and Reconstruction Li, Baicheng Yan, Zike Wu, Dong Zha, Hongbin Computer Vision and Pattern Recognition Human behaviors are the major causes of scene dynamics and inherently contain rich cues regarding the dynamics. This paper formalizes a new task of proactive scene decomposition and reconstruction, an online approach that leverages human-object interactions to iteratively disassemble and reconstruct the environment. By observing these intentional interactions, we can dynamically refine the decomposition and reconstruction process, addressing inherent ambiguities in static object-level reconstruction. The proposed system effectively integrates multiple tasks in dynamic environments such as accurate camera and object pose estimation, instance decomposition, and online map updating, capitalizing on cues from human-object interactions in egocentric live streams for a flexible, progressive alternative to conventional object-level reconstruction methods. Aided by the Gaussian splatting technique, accurate and consistent dynamic scene modeling is achieved with photorealistic and efficient rendering. The efficacy is validated in multiple real-world scenarios with promising advantages. |
| title | Proactive Scene Decomposition and Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.16272 |