Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915594069082112 |
|---|---|
| author | Shi, Yuang Gasparini, Simone Morin, Géraldine Yang, Chenggang Ooi, Wei Tsang |
| author_facet | Shi, Yuang Gasparini, Simone Morin, Géraldine Yang, Chenggang Ooi, Wei Tsang |
| contents | 3D Gaussian Splatting (3DGS) has emerged as a promising representation for photorealistic rendering of 3D scenes. However, its high storage requirements pose significant challenges for practical applications. We observe that Gaussians exhibit distinct roles and characteristics that are analogous to traditional artistic techniques -- Like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features like edges and contours; While other Gaussians represent broader, smoother regions, that are analogous to broader brush strokes that add volume and depth to a painting. Based on this observation, we propose a novel hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which define scene boundaries, and (ii) Patch Gaussians, which cover smooth regions. Sketch Gaussians are efficiently encoded using parametric models, leveraging their geometric coherence, while Patch Gaussians undergo optimized pruning, retraining, and vector quantization to maintain volumetric consistency and storage efficiency. Our comprehensive evaluation across diverse indoor and outdoor scenes demonstrates that this structure-aware approach achieves up to 32.62% improvement in PSNR, 19.12% in SSIM, and 45.41% in LPIPS at equivalent model sizes, and correspondingly, for an indoor scene, our model maintains the visual quality with 2.3% of the original model size. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_13045 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes Shi, Yuang Gasparini, Simone Morin, Géraldine Yang, Chenggang Ooi, Wei Tsang Computer Vision and Pattern Recognition Multimedia 3D Gaussian Splatting (3DGS) has emerged as a promising representation for photorealistic rendering of 3D scenes. However, its high storage requirements pose significant challenges for practical applications. We observe that Gaussians exhibit distinct roles and characteristics that are analogous to traditional artistic techniques -- Like how artists first sketch outlines before filling in broader areas with color, some Gaussians capture high-frequency features like edges and contours; While other Gaussians represent broader, smoother regions, that are analogous to broader brush strokes that add volume and depth to a painting. Based on this observation, we propose a novel hybrid representation that categorizes Gaussians into (i) Sketch Gaussians, which define scene boundaries, and (ii) Patch Gaussians, which cover smooth regions. Sketch Gaussians are efficiently encoded using parametric models, leveraging their geometric coherence, while Patch Gaussians undergo optimized pruning, retraining, and vector quantization to maintain volumetric consistency and storage efficiency. Our comprehensive evaluation across diverse indoor and outdoor scenes demonstrates that this structure-aware approach achieves up to 32.62% improvement in PSNR, 19.12% in SSIM, and 45.41% in LPIPS at equivalent model sizes, and correspondingly, for an indoor scene, our model maintains the visual quality with 2.3% of the original model size. |
| title | Sketch and Patch: Efficient 3D Gaussian Representation for Man-Made Scenes |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2501.13045 |