Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2512.13796 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908714367188992 |
|---|---|
| author | Rong, Victor Held, Jan Chu, Victor Rebain, Daniel Van Droogenbroeck, Marc Kutulakos, Kiriakos N. Tagliasacchi, Andrea Lindell, David B. |
| author_facet | Rong, Victor Held, Jan Chu, Victor Rebain, Daniel Van Droogenbroeck, Marc Kutulakos, Kiriakos N. Tagliasacchi, Andrea Lindell, David B. |
| contents | Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a representation that goes beyond point-based rendering and decouples geometry and appearance in order to achieve a compact representation. We use surfels for geometry and a combination of a global neural field and per-primitive colours for appearance. The neural field textures a fixed number of primitives for each pixel, ensuring that the added compute is low. Our representation matches the perceptual quality of 3D Gaussian splatting while using $9.7\times$ fewer primitives and $5.5\times$ less memory on outdoor scenes and using $31\times$ fewer primitives and $3.7\times$ less memory on indoor scenes. Our representation also renders twice as fast as existing textured primitives while improving upon their visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_13796 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries Rong, Victor Held, Jan Chu, Victor Rebain, Daniel Van Droogenbroeck, Marc Kutulakos, Kiriakos N. Tagliasacchi, Andrea Lindell, David B. Computer Vision and Pattern Recognition Though Gaussian splatting has achieved impressive results in novel view synthesis, it requires millions of primitives to model highly textured scenes, even when the geometry of the scene is simple. We propose a representation that goes beyond point-based rendering and decouples geometry and appearance in order to achieve a compact representation. We use surfels for geometry and a combination of a global neural field and per-primitive colours for appearance. The neural field textures a fixed number of primitives for each pixel, ensuring that the added compute is low. Our representation matches the perceptual quality of 3D Gaussian splatting while using $9.7\times$ fewer primitives and $5.5\times$ less memory on outdoor scenes and using $31\times$ fewer primitives and $3.7\times$ less memory on indoor scenes. Our representation also renders twice as fast as existing textured primitives while improving upon their visual quality. |
| title | Nexels: Neurally-Textured Surfels for Real-Time Novel View Synthesis with Sparse Geometries |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.13796 |