The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in torn or drifting textures, or remaining trapped by the resolution ceiling of explicit voxels, forfeiting fine texture detail. In this work, we propose Sparse-Up, a memory-efficient, high-fidelity texture modeling framework that effectively preserves high-frequency details. We use sparse voxels to guide texture reconstruction and ensure multi-view consistency, while leveraging surface anchoring and view-domain partitioning to break through resolution constraints. Surface anchoring employs a learnable upsampling strategy to constrain voxels to the mesh surface, eliminating over 70% of redundant voxels present in traditional voxel upsampling. View-domain partitioning introduces an image patch-guided voxel partitioning scheme, supervising and back-propagating gradients only on visible local patches. Through these two strategies, we can significantly reduce memory consumption during high-resolution voxel training without sacrificing geometric consistency, while preserving high-frequency details in textures.
@article{arxiv.2509.23646,
title = {Sparse-Up: Learnable Sparse Upsampling for 3D Generation with High-Fidelity Textures},
author = {Lu Xiao and Jiale Zhang and Yang Liu and Taicheng Huang and Xin Tian},
journal= {arXiv preprint arXiv:2509.23646},
year = {2025}
}