SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene 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_ | 1866908730654720000 |
|---|---|
| author | Jain, Neham Jong, Andrew Scherer, Sebastian Gkioulekas, Ioannis |
| author_facet | Jain, Neham Jong, Andrew Scherer, Sebastian Gkioulekas, Ioannis |
| contents | Smoke in real-world scenes can severely degrade image quality and hamper visibility. Recent image restoration methods either rely on data-driven priors that are susceptible to hallucinations, or are limited to static low-density smoke. We introduce SmokeSeer, a method for simultaneous 3D scene reconstruction and smoke removal from multi-view video sequences. Our method uses thermal and RGB images, leveraging the reduced scattering in thermal images to see through smoke. We build upon 3D Gaussian splatting to fuse information from the two image modalities, and decompose the scene into smoke and non-smoke components. Unlike prior work, SmokeSeer handles a broad range of smoke densities and adapts to temporally varying smoke. We validate our method on synthetic data and a new real-world smoke dataset with RGB and thermal images. We provide an open-source implementation and data on the project website. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction Jain, Neham Jong, Andrew Scherer, Sebastian Gkioulekas, Ioannis Computer Vision and Pattern Recognition Smoke in real-world scenes can severely degrade image quality and hamper visibility. Recent image restoration methods either rely on data-driven priors that are susceptible to hallucinations, or are limited to static low-density smoke. We introduce SmokeSeer, a method for simultaneous 3D scene reconstruction and smoke removal from multi-view video sequences. Our method uses thermal and RGB images, leveraging the reduced scattering in thermal images to see through smoke. We build upon 3D Gaussian splatting to fuse information from the two image modalities, and decompose the scene into smoke and non-smoke components. Unlike prior work, SmokeSeer handles a broad range of smoke densities and adapts to temporally varying smoke. We validate our method on synthetic data and a new real-world smoke dataset with RGB and thermal images. We provide an open-source implementation and data on the project website. |
| title | SmokeSeer: 3D Gaussian Splatting for Smoke Removal and Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17329 |