TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916660129038336 |
|---|---|
| author | Xiong, Bojun Liu, Jialun Hu, Jiakui Wu, Chenming Wu, Jinbo Liu, Xing Zhao, Chen Ding, Errui Lian, Zhouhui |
| author_facet | Xiong, Bojun Liu, Jialun Hu, Jiakui Wu, Chenming Wu, Jinbo Liu, Xing Zhao, Chen Ding, Errui Lian, Zhouhui |
| contents | Physically Based Rendering (PBR) materials play a crucial role in modern graphics, enabling photorealistic rendering across diverse environment maps. Developing an effective and efficient algorithm that is capable of automatically generating high-quality PBR materials rather than RGB texture for 3D meshes can significantly streamline the 3D content creation. Most existing methods leverage pre-trained 2D diffusion models for multi-view image synthesis, which often leads to severe inconsistency between the generated textures and input 3D meshes. This paper presents TexGaussian, a novel method that uses octant-aligned 3D Gaussian Splatting for rapid PBR material generation. Specifically, we place each 3D Gaussian on the finest leaf node of the octree built from the input 3D mesh to render the multi-view images not only for the albedo map but also for roughness and metallic. Moreover, our model is trained in a regression manner instead of diffusion denoising, capable of generating the PBR material for a 3D mesh in a single feed-forward process. Extensive experiments on publicly available benchmarks demonstrate that our method synthesizes more visually pleasing PBR materials and runs faster than previous methods in both unconditional and text-conditional scenarios, exhibiting better consistency with the given geometry. Our code and trained models are available at https://3d-aigc.github.io/TexGaussian. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_19654 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting Xiong, Bojun Liu, Jialun Hu, Jiakui Wu, Chenming Wu, Jinbo Liu, Xing Zhao, Chen Ding, Errui Lian, Zhouhui Computer Vision and Pattern Recognition Graphics Physically Based Rendering (PBR) materials play a crucial role in modern graphics, enabling photorealistic rendering across diverse environment maps. Developing an effective and efficient algorithm that is capable of automatically generating high-quality PBR materials rather than RGB texture for 3D meshes can significantly streamline the 3D content creation. Most existing methods leverage pre-trained 2D diffusion models for multi-view image synthesis, which often leads to severe inconsistency between the generated textures and input 3D meshes. This paper presents TexGaussian, a novel method that uses octant-aligned 3D Gaussian Splatting for rapid PBR material generation. Specifically, we place each 3D Gaussian on the finest leaf node of the octree built from the input 3D mesh to render the multi-view images not only for the albedo map but also for roughness and metallic. Moreover, our model is trained in a regression manner instead of diffusion denoising, capable of generating the PBR material for a 3D mesh in a single feed-forward process. Extensive experiments on publicly available benchmarks demonstrate that our method synthesizes more visually pleasing PBR materials and runs faster than previous methods in both unconditional and text-conditional scenarios, exhibiting better consistency with the given geometry. Our code and trained models are available at https://3d-aigc.github.io/TexGaussian. |
| title | TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2411.19654 |