3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering
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_ | 1866917892892655616 |
|---|---|
| author | Krishnan, Meenakshi Fowl, Liam Duraiswami, Ramani |
| author_facet | Krishnan, Meenakshi Fowl, Liam Duraiswami, Ramani |
| contents | Differentiable 3D Gaussian splatting has emerged as an efficient and flexible rendering technique for representing complex scenes from a collection of 2D views and enabling high-quality real-time novel-view synthesis. However, its reliance on photometric losses can lead to imprecisely reconstructed geometry and extracted meshes, especially in regions with high curvature or fine detail. We propose a novel regularization method using the gradients of a signed distance function estimated from the Gaussians, to improve the quality of rendering while also extracting a surface mesh. The regularizing normal supervision facilitates better rendering and mesh reconstruction, which is crucial for downstream applications in video generation, animation, AR-VR and gaming. We demonstrate the effectiveness of our approach on datasets such as Mip-NeRF360, Tanks and Temples, and Deep-Blending. Our method scores higher on photorealism metrics compared to other mesh extracting rendering methods without compromising mesh quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08370 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | 3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering Krishnan, Meenakshi Fowl, Liam Duraiswami, Ramani Graphics Computer Vision and Pattern Recognition Differentiable 3D Gaussian splatting has emerged as an efficient and flexible rendering technique for representing complex scenes from a collection of 2D views and enabling high-quality real-time novel-view synthesis. However, its reliance on photometric losses can lead to imprecisely reconstructed geometry and extracted meshes, especially in regions with high curvature or fine detail. We propose a novel regularization method using the gradients of a signed distance function estimated from the Gaussians, to improve the quality of rendering while also extracting a surface mesh. The regularizing normal supervision facilitates better rendering and mesh reconstruction, which is crucial for downstream applications in video generation, animation, AR-VR and gaming. We demonstrate the effectiveness of our approach on datasets such as Mip-NeRF360, Tanks and Temples, and Deep-Blending. Our method scores higher on photorealism metrics compared to other mesh extracting rendering methods without compromising mesh quality. |
| title | 3D Gaussian Splatting with Normal Information for Mesh Extraction and Improved Rendering |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.08370 |