Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.09243 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912823210147840 |
|---|---|
| author | Hsu, Sheng-Chi Yen, Ting-Yu Hung, Shih-Hsuan Chu, Hung-Kuo |
| author_facet | Hsu, Sheng-Chi Yen, Ting-Yu Hung, Shih-Hsuan Chu, Hung-Kuo |
| contents | Gaussian Splatting has emerged as a powerful representation for high-quality, real-time 3D scene rendering. While recent works extend Gaussians with learnable textures to enrich visual appearance, existing approaches allocate a fixed square texture per primitive, leading to inefficient memory usage and limited adaptability to scene variability. In this paper, we introduce adaptive anisotropic textured Gaussians (A$^2$TG), a novel representation that generalizes textured Gaussians by equipping each primitive with an anisotropic texture. Our method employs a gradient-guided adaptive rule to jointly determine texture resolution and aspect ratio, enabling non-uniform, detail-aware allocation that aligns with the anisotropic nature of Gaussian splats. This design significantly improves texture efficiency, reducing memory consumption while enhancing image quality. Experiments on multiple benchmark datasets demonstrate that A TG consistently outperforms fixed-texture Gaussian Splatting methods, achieving comparable rendering fidelity with substantially lower memory requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_09243 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation Hsu, Sheng-Chi Yen, Ting-Yu Hung, Shih-Hsuan Chu, Hung-Kuo Computer Vision and Pattern Recognition Gaussian Splatting has emerged as a powerful representation for high-quality, real-time 3D scene rendering. While recent works extend Gaussians with learnable textures to enrich visual appearance, existing approaches allocate a fixed square texture per primitive, leading to inefficient memory usage and limited adaptability to scene variability. In this paper, we introduce adaptive anisotropic textured Gaussians (A$^2$TG), a novel representation that generalizes textured Gaussians by equipping each primitive with an anisotropic texture. Our method employs a gradient-guided adaptive rule to jointly determine texture resolution and aspect ratio, enabling non-uniform, detail-aware allocation that aligns with the anisotropic nature of Gaussian splats. This design significantly improves texture efficiency, reducing memory consumption while enhancing image quality. Experiments on multiple benchmark datasets demonstrate that A TG consistently outperforms fixed-texture Gaussian Splatting methods, achieving comparable rendering fidelity with substantially lower memory requirements. |
| title | A$^2$TG: Adaptive Anisotropic Textured Gaussians for Efficient 3D Scene Representation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.09243 |