SparseFlex：高分辨率與任意拓撲的三維形狀建模

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

創建具有任意拓撲結構的高保真3D網格，包括開放表面和複雜內部結構，仍然是一個重大挑戰。現有的隱式場方法通常需要耗時且會降低細節的封閉轉換，而其他方法則難以處理高分辨率。本文介紹了SparseFlex，一種新穎的稀疏結構等值面表示方法，能夠直接從渲染損失中實現高達1024^3分辨率的可微分網格重建。SparseFlex結合了Flexicubes的精度與稀疏體素結構，將計算集中在表面鄰近區域，並高效處理開放表面。關鍵在於，我們引入了一種視錐感知的分段體素訓練策略，該策略在渲染時僅激活相關體素，顯著降低了內存消耗，並實現了高分辨率訓練。這也首次允許僅通過渲染監督來重建網格內部結構。基於此，我們展示了一個完整的形狀建模流程，通過訓練變分自編碼器（VAE）和校正流變換器來生成高質量的3D形狀。我們的實驗顯示了最先進的重建精度，與之前的方法相比，Chamfer Distance減少了約82%，F-score提高了約88%，並展示了生成具有任意拓撲結構的高分辨率、細節豐富的3D形狀的能力。通過實現基於渲染損失的高分辨率、可微分網格重建與生成，SparseFlex在3D形狀表示與建模領域顯著推動了技術前沿。

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.