RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909258537238528 |
|---|---|
| author | Nguyen, Thang-Anh-Quan Roldão, Luis Piasco, Nathan Bennehar, Moussab Tsishkou, Dzmitry |
| author_facet | Nguyen, Thang-Anh-Quan Roldão, Luis Piasco, Nathan Bennehar, Moussab Tsishkou, Dzmitry |
| contents | The task of separating dynamic objects from static environments using NeRFs has been widely studied in recent years. However, capturing large-scale scenes still poses a challenge due to their complex geometric structures and unconstrained dynamics. Without the help of 3D motion cues, previous methods often require simplified setups with slow camera motion and only a few/single dynamic actors, leading to suboptimal solutions in most urban setups. To overcome such limitations, we present RoDUS, a pipeline for decomposing static and dynamic elements in urban scenes, with thoughtfully separated NeRF models for moving and non-moving components. Our approach utilizes a robust kernel-based initialization coupled with 4D semantic information to selectively guide the learning process. This strategy enables accurate capturing of the dynamics in the scene, resulting in reduced floating artifacts in the reconstructed background, all by using self-supervision. Notably, experimental evaluations on KITTI-360 and Pandaset datasets demonstrate the effectiveness of our method in decomposing challenging urban scenes into precise static and dynamic components. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_09419 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes Nguyen, Thang-Anh-Quan Roldão, Luis Piasco, Nathan Bennehar, Moussab Tsishkou, Dzmitry Computer Vision and Pattern Recognition The task of separating dynamic objects from static environments using NeRFs has been widely studied in recent years. However, capturing large-scale scenes still poses a challenge due to their complex geometric structures and unconstrained dynamics. Without the help of 3D motion cues, previous methods often require simplified setups with slow camera motion and only a few/single dynamic actors, leading to suboptimal solutions in most urban setups. To overcome such limitations, we present RoDUS, a pipeline for decomposing static and dynamic elements in urban scenes, with thoughtfully separated NeRF models for moving and non-moving components. Our approach utilizes a robust kernel-based initialization coupled with 4D semantic information to selectively guide the learning process. This strategy enables accurate capturing of the dynamics in the scene, resulting in reduced floating artifacts in the reconstructed background, all by using self-supervision. Notably, experimental evaluations on KITTI-360 and Pandaset datasets demonstrate the effectiveness of our method in decomposing challenging urban scenes into precise static and dynamic components. |
| title | RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenes |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.09419 |