LoG3D: Ultra-High-Resolution 3D Shape Modeling via Local-to-Global Partitioning
This addresses the problem of 3D content creation for applications like computer graphics and simulation by enabling more efficient and detailed modeling of non-manifold geometries, representing an incremental improvement over existing methods.
The paper tackled the challenge of generating high-fidelity 3D shapes with complex topologies by proposing a 3D VAE framework using unsigned distance fields and a local-to-global architecture, achieving state-of-the-art performance in reconstruction accuracy and generative quality with scaling to ultra-high resolutions up to 2048^3.
Generating high-fidelity 3D contents remains a fundamental challenge due to the complexity of representing arbitrary topologies-such as open surfaces and intricate internal structures-while preserving geometric details. Prevailing methods based on signed distance fields (SDFs) are hampered by costly watertight preprocessing and struggle with non-manifold geometries, while point-cloud representations often suffer from sampling artifacts and surface discontinuities. To overcome these limitations, we propose a novel 3D variational autoencoder (VAE) framework built upon unsigned distance fields (UDFs)-a more robust and computationally efficient representation that naturally handles complex and incomplete shapes. Our core innovation is a local-to-global (LoG) architecture that processes the UDF by partitioning it into uniform subvolumes, termed UBlocks. This architecture couples 3D convolutions for capturing local detail with sparse transformers for enforcing global coherence. A Pad-Average strategy further ensures smooth transitions at subvolume boundaries during reconstruction. This modular design enables seamless scaling to ultra-high resolutions up to $2048^3$-a regime previously unattainable for 3D VAEs. Experiments demonstrate state-of-the-art performance in both reconstruction accuracy and generative quality, yielding superior surface smoothness and geometric flexibility.