Problem
Research questions and friction points this paper is trying to address.
high-resolution
multi-view diffusion
3D texturing
computational prohibitive
UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing
๐ค AI Summary
UltraTex้่ฟ่ๆฏไปค็ไธขๅผใๅ็จ็ๆณจๆๅๅๅๆฏๆ็ฅVAE่งฃ็ ๆนๆณ๏ผ่งฃๅณไบ้ซๅ่พจ็3D็บน็็ๆไธญ็่ฎก็ฎๆ็ๅ็ป่ไฟ็้ฎ้ขใ
๐ Abstract
High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown promising results for image-guided 3D texturing, but they are typically constrained to low operating resolutions such as 512 or 768, making it difficult to preserve high-frequency details from high-resolution reference images. Scaling this paradigm to 2048 resolution is computationally prohibitive, as the unified multi-view sequence exceeds 212K tokens and incurs excessive memory and latency. In this paper, we present UltraTex, an efficient end-to-end framework for high-resolution multi-view diffusion-based 3D texturing. Our key observation is that object-centric multi-view renderings contain two major sources of redundancy: background-induced sequence redundancy and sparse token interactions within the foreground. To address them, we introduce Background Token Dropping, which removes background tokens before the DiT backbone, and Block-Sparse Attention, which reduces attention computation over the retained foreground sequence. To enable efficient foreground-only inference while avoiding reconstruction artifacts, we further design Foreground-Aware VAE Decoding to ensure the quality of the final high-resolution views. To satisfy the demanding data requirements of 2K-resolution multi-view diffusion training, we construct G-buffer TexVerse, a large-scale, ultra-high-resolution multi-view rendering dataset covering over 268,000 3D assets. Extensive experiments show that UltraTex generates visually faithful textures with rich fine-grained details, while substantially improving efficiency, achieving $20.6\times$--$91.1\times$ training speedup and $22.3\times$--$74.6\times$ end-to-end inference speedup over the baseline on common samples in our dataset. Code and data is at https://yiboz2001.github.io/UltraTex.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Background Token Dropping
Block-Sparse Attention
Foreground-Aware VAE Decoding
G-buffer TexVerse
๐ Similar Papers
No similar papers found.
๐ผ Related Jobs
