D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914125693583360 |
|---|---|
| author | Han, Jisang An, Honggyu Jung, Jaewoo Narihira, Takuya Seo, Junyoung Fukuda, Kazumi Kim, Chaehyun Hong, Sunghwan Mitsufuji, Yuki Kim, Seungryong |
| author_facet | Han, Jisang An, Honggyu Jung, Jaewoo Narihira, Takuya Seo, Junyoung Fukuda, Kazumi Kim, Chaehyun Hong, Sunghwan Mitsufuji, Yuki Kim, Seungryong |
| contents | In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, that are originally designed for static 3D scene reconstruction. Although these methods provide an elegant and powerful solution in static settings, they struggle in the presence of dynamic motions that disrupt alignment based solely on camera poses. To overcome this, we propose $D^2USt3R$ that directly regresses Static-Dynamic Aligned Pointmaps (SDAP) that simultaneiously capture both static and dynamic 3D scene geometry. By explicitly incorporating both spatial and temporal aspects, our approach successfully encapsulates 3D dense correspondence to the proposed pointmaps, enhancing downstream tasks. Extensive experimental evaluations demonstrate that our proposed approach consistently achieves superior 3D reconstruction performance across various datasets featuring complex motions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06264 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes Han, Jisang An, Honggyu Jung, Jaewoo Narihira, Takuya Seo, Junyoung Fukuda, Kazumi Kim, Chaehyun Hong, Sunghwan Mitsufuji, Yuki Kim, Seungryong Computer Vision and Pattern Recognition In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DUSt3R, that are originally designed for static 3D scene reconstruction. Although these methods provide an elegant and powerful solution in static settings, they struggle in the presence of dynamic motions that disrupt alignment based solely on camera poses. To overcome this, we propose $D^2USt3R$ that directly regresses Static-Dynamic Aligned Pointmaps (SDAP) that simultaneiously capture both static and dynamic 3D scene geometry. By explicitly incorporating both spatial and temporal aspects, our approach successfully encapsulates 3D dense correspondence to the proposed pointmaps, enhancing downstream tasks. Extensive experimental evaluations demonstrate that our proposed approach consistently achieves superior 3D reconstruction performance across various datasets featuring complex motions. |
| title | D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.06264 |