# 3D Texturing

Tex-Zero introduces a data-construction pipeline that treats each 2D image as a plane in 3D space and applies patch-wise random rotations and aggregation, training a native 3D texture generation VAE and DiT without any real 3D assets and achieving high-fidelity texture reconstruction and generation on real 3D assets, outperforming baselines such as NaTex and TRELLIS.2 in six-view and front-view evaluations.

Tex-Zero introduces a data-construction pipeline that treats each 2D image as a plane in 3D space and applies patch-wise random rotations and aggregation, training a native 3D texture generation VAE and DiT without any real 3D assets and achieving high-fidelity texture reconstruction and generation on real 3D assets, outperforming baselines such as NaTex and TRELLIS.2 in six-view and front-view evaluations.

UltraTex is an end-to-end multi-view diffusion framework that scales image-guided 3D texturing from 512/768 to 2048 resolution through Background Token Dropping, Block-Sparse Attention, and Foreground-Aware VAE Decoding, and it builds G-buffer TexVerse covering over 268,000 3D assets, achieving 20.6-91.1x training speedup and 22.3-74.6x end-to-end inference speedup within the dataset's common foreground-ratio range of 10%-30%.

UltraTex is an end-to-end multi-view diffusion framework that scales image-guided 3D texturing from 512/768 to 2048 resolution through Background Token Dropping, Block-Sparse Attention, and Foreground-Aware VAE Decoding, and it builds G-buffer TexVerse covering over 268,000 3D assets, achieving 20.6-91.1x training speedup and 22.3-74.6x end-to-end inference speedup within the dataset's common foreground-ratio range of 10%-30%.