NeRF-Texture: Texture Synthesis with Neural Radiance Fields

1ICT, CAS 2UCAS 3ARC Lab, Tencent PCG 4Cardiff University


Texture synthesis is a fundamental problem in computer graphics that would benefit various applications. Existing methods are effective in handling 2D image textures. In contrast, many real-world textures contain meso-structure in the 3D geometry space, such as grass, leaves, and fabrics, which cannot be effectively modeled using only 2D image textures. We propose a novel texture synthesis method with Neural Radiance Fields (NeRF) to capture and synthesize textures from given multi-view images. In the proposed NeRF texture representation, a scene with fine geometric details is disentangled into the meso-structure textures and the underlying base shape. This allows textures with meso-structure to be effectively learned as latent features situated on the base shape, which are fed into a NeRF decoder trained simultaneously to represent the rich view-dependent appearance. Using this implicit representation, we can synthesize NeRF-based textures through patch matching of latent features. However, inconsistencies between the metrics of the reconstructed content space and the latent feature space may compromise the synthesis quality. To enhance matching performance, we further regularize the distribution of latent features by incorporating a clustering constraint. Experimental results and evaluations demonstrate the effectiveness of our approach.


Texture Capture and Synthesis

You can capture real-world textures and synthesize them with NeRF-Texture.

Application of Synthesized Texture

Textures synthesized by NeRF-Texture can be applied to decorate novel shapes.


        author = {Huang, Yi-Hua and Cao, Yan-Pei and Lai, Yu-Kun and Shan, Ying and Gao, Lin},
        title = {NeRF-Texture: Texture Synthesis with Neural Radiance Fields},
        year = {2023},
        isbn = {9798400701597},
        booktitle = {ACM SIGGRAPH 2023 Conference Proceedings},
        keywords = {Neural Radiance Fields, Texture Synthesis, Meso-structure Texture},


The website template is borrowed from Nerfies.