SparseFlex：高分辨率与任意拓扑的三维形状建模

SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling

March 27, 2025

作者: Xianglong He, Zi-Xin Zou, Chia-Hao Chen, Yuan-Chen Guo, Ding Liang, Chun Yuan, Wanli Ouyang, Yan-Pei Cao, Yangguang Li

cs.AI

摘要

创建具有任意拓扑结构的高保真三维网格，包括开放表面和复杂内部结构，仍然是一个重大挑战。现有的隐式场方法通常需要昂贵且细节损失严重的封闭转换，而其他方法则难以处理高分辨率。本文提出了SparseFlex，一种新颖的稀疏结构等值面表示方法，能够直接从渲染损失中实现分辨率高达1024^3的可微分网格重建。SparseFlex结合了Flexicubes的精确性与稀疏体素结构，将计算集中在表面邻近区域，并高效处理开放表面。关键的是，我们引入了一种视锥感知的分段体素训练策略，仅在渲染时激活相关体素，显著减少了内存消耗并实现了高分辨率训练。这也首次实现了仅通过渲染监督重建网格内部结构。在此基础上，我们通过训练变分自编码器（VAE）和整流流变压器，展示了一个完整的形状建模流程，用于高质量三维形状生成。我们的实验展示了最先进的重建精度，与之前的方法相比，Chamfer Distance减少了约82%，F-score提高了约88%，并展示了生成具有任意拓扑结构的高分辨率、细节丰富的三维形状。通过实现高分辨率、可微分网格重建与生成，SparseFlex在三维形状表示与建模领域显著推进了技术前沿。

English

Creating high-fidelity 3D meshes with arbitrary topology, including open surfaces and complex interiors, remains a significant challenge. Existing implicit field methods often require costly and detail-degrading watertight conversion, while other approaches struggle with high resolutions. This paper introduces SparseFlex, a novel sparse-structured isosurface representation that enables differentiable mesh reconstruction at resolutions up to 1024^3 directly from rendering losses. SparseFlex combines the accuracy of Flexicubes with a sparse voxel structure, focusing computation on surface-adjacent regions and efficiently handling open surfaces. Crucially, we introduce a frustum-aware sectional voxel training strategy that activates only relevant voxels during rendering, dramatically reducing memory consumption and enabling high-resolution training. This also allows, for the first time, the reconstruction of mesh interiors using only rendering supervision. Building upon this, we demonstrate a complete shape modeling pipeline by training a variational autoencoder (VAE) and a rectified flow transformer for high-quality 3D shape generation. Our experiments show state-of-the-art reconstruction accuracy, with a ~82% reduction in Chamfer Distance and a ~88% increase in F-score compared to previous methods, and demonstrate the generation of high-resolution, detailed 3D shapes with arbitrary topology. By enabling high-resolution, differentiable mesh reconstruction and generation with rendering losses, SparseFlex significantly advances the state-of-the-art in 3D shape representation and modeling.