LiDPM: Rethinking Point Diffusion for Lidar Scene Completion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912485639979008 |
|---|---|
| author | Martyniuk, Tetiana Puy, Gilles Boulch, Alexandre Marlet, Renaud de Charette, Raoul |
| author_facet | Martyniuk, Tetiana Puy, Gilles Boulch, Alexandre Marlet, Renaud de Charette, Raoul |
| contents | Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_17791 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LiDPM: Rethinking Point Diffusion for Lidar Scene Completion Martyniuk, Tetiana Puy, Gilles Boulch, Alexandre Marlet, Renaud de Charette, Raoul Computer Vision and Pattern Recognition Robotics Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise over a broad field of view. The latest works addressing scene completion with diffusion models tackle this problem by reformulating the original DDPM as a local diffusion process. It contrasts with the common practice of operating at the level of objects, where vanilla DDPMs are currently used. In this work, we close the gap between these two lines of work. We identify approximations in the local diffusion formulation, show that they are not required to operate at the scene level, and that a vanilla DDPM with a well-chosen starting point is enough for completion. Finally, we demonstrate that our method, LiDPM, leads to better results in scene completion on SemanticKITTI. The project page is https://astra-vision.github.io/LiDPM . |
| title | LiDPM: Rethinking Point Diffusion for Lidar Scene Completion |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2504.17791 |