Textured Gaussians for Enhanced 3D Scene Appearance Modeling
Brian Chao, Hung-Yu Tseng, Lorenzo Porzi, Chen Gao, Tuotuo Li, Qinbo Li, Ayush Saraf, Jia-Bin Huang, Johannes Kopf, Gordon Wetzstein, Changil Kim
Abstract
3D Gaussian Splatting (3DGS) has emerged as the state-of-the-art 3D reconstruction technique, offering high-quality results with fast training and rendering. However, its expressivity is limited as pixels covered by the same Gaussian share identical colors aside from a Gaussian falloff scaling factor, and individual Gaussians can only represent simple ellipsoids geometrically. To overcome these limitations, we integrate texture and alpha mapping from traditional graphics with 3DGS. Our approach augments each Gaussian with alpha, RGB, or RGBA texture maps to model spatially varying color and opacity across each Gaussian’s extent. This allows Gaussians to represent richer texture patterns and geometric structures beyond single-color ellipsoids. Notably, alpha-only texture maps significantly improve Gaussian expressivity, while further augmenting with RGB texture maps achieve maximum expressivity. We validate our method on a wide variety of standard benchmark datasets and our own custom captures at both the object and scene levels, and demonstrate image quality improvements over existing methods while using a similar or lower number of Gaussians.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 66a96c5e-0bef-4212-9950-fac658c01e0eCited by top-tier papers16
- Splat the Net: Radiance Fields with Splattable Neural Primitivesxilong zhou, Bao-Huy Nguyen, Loïc Magne, Vladislav Golyanik et al.ICLR 2026 · 8 citations
- Neural Shell Texture Splatting: More Details and Fewer PrimitivesXin Zhang, Anpei Chen, Jincheng Xiong, Pinxuan Dai et al.ICCV 2025 · 6 citations
- DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field SimplificationKenji Tojo, Bernd Bickel, Nobuyuki UmetaniCVPR 2026 · 5 citations
- Quadratic Gaussian Splatting: High Quality Surface Reconstruction with Second-Order Geometric PrimitivesZiyu Zhang, Binbin Huang, Hanqing Jiang, Liyang Zhou et al.ICCV 2025 · 5 citations
- Holistic Large-Scale Scene Reconstruction via Mixed Gaussian SplattingChuandong Liu, Huijiao Wang, Lei Yu, Gui-Song XiaNeurIPS 2025 · 4 citations
Builds on28
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 4,089 citations
- NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view ReconstructionPeng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt et al.NeurIPS 2021 · 2,500 citations
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Dor Verbin, Pratul P. Srinivasan et al.CVPR 2022 · 1,603 citations
- PlenOctrees for Real-time Rendering of Neural Radiance FieldsAlex Yu, Ruilong Li, Matthew Tancik, Hao Li et al.ICCV 2021 · 1,284 citations
Related papers
- Wavelet-GS: 3D Gaussian Splatting with Wavelet DecompositionBeizhen Zhao, Yifan Zhou, Sicheng Yu, Zijian Wang et al.ACM MM 2025 · 1 citation
- IBGS: Image-Based Gaussian SplattingHoang Chuong Nguyen, Wei Mao, José M. Álvarez, Miaomiao LiuNeurIPS 2025 · 1 citation
- SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAMPengchong Hu, Zhizhong HanCVPR 2026 · 2 citations
- Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian SplattingJunseo Koo, Jinseo Jeong, Gunhee KimAAAI 2026
- MPGS: Multi-Plane Gaussian Splatting for Compact Scenes RenderingDeqi Li, Shi-Sheng Huang, Hua HuangIEEE VR 2025 · 11 citations
