EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910958286274560 |
|---|---|
| author | Yura, Toshiya Mirzaei, Ashkan Gilitschenski, Igor |
| author_facet | Yura, Toshiya Mirzaei, Ashkan Gilitschenski, Igor |
| contents | We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address the novel view synthesis challenge in the presence of fast camera motion. For initialization of the optimization process, our approach uses prior knowledge encoded in an event-to-video model. We also use spline interpolation for obtaining high quality poses along the event camera trajectory. This enhances the reconstruction quality from fast-moving cameras while overcoming the computational limitations traditionally associated with event-based Neural Radiance Field (NeRF) methods. Our experimental evaluation demonstrates that our results achieve higher visual fidelity and better performance than existing event-based NeRF approaches while being an order of magnitude faster to render. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07293 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering Yura, Toshiya Mirzaei, Ashkan Gilitschenski, Igor Computer Vision and Pattern Recognition We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address the novel view synthesis challenge in the presence of fast camera motion. For initialization of the optimization process, our approach uses prior knowledge encoded in an event-to-video model. We also use spline interpolation for obtaining high quality poses along the event camera trajectory. This enhances the reconstruction quality from fast-moving cameras while overcoming the computational limitations traditionally associated with event-based Neural Radiance Field (NeRF) methods. Our experimental evaluation demonstrates that our results achieve higher visual fidelity and better performance than existing event-based NeRF approaches while being an order of magnitude faster to render. |
| title | EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.07293 |