基于掩码的体素扩散用于联合几何和颜色修复
Mask-Conditioned Voxel Diffusion for Joint Geometry and Color Inpainting
AI总结：
本文提出基于掩码的体素扩散方法，用于修复受损3D物体的几何和颜色，通过两阶段框架实现更完整和一致的修复效果。
摘要：
我们提出了一种轻量级的两阶段框架，用于修复受损的3D物体的几何和颜色，受数字修复文化遗产文物的启发。该流程将损坏定位与重建分开。在第一阶段，一个2D卷积网络在从体素化物体中提取的RGB切片上预测损坏掩码，这些预测被聚合为体素掩码。在第二阶段，基于扩散的3D U-Net直接在体素网格上进行掩码条件修复，重建几何和颜色的同时保持观察区域。模型使用一个综合目标联合预测占用和颜色，该目标结合了占用重建、掩码颜色重建和感知正则化。我们在一个经过精心挑选的具有合成损坏的纹理文物集合上评估了该方法，使用标准的几何和颜色度量标准。与基于对称性的基线相比，我们的方法在固定32^3分辨率下产生了更完整的几何和更一致的颜色重建。总体而言，结果表明，显式的掩码条件是指导体素扩散模型进行联合3D几何和颜色修复的一种实用方法。
英文摘要：
We present a lightweight two-stage framework for joint geometry and color inpainting of damaged 3D objects, motivated by the digital restoration of cultural heritage artifacts. The pipeline separates damage localization from reconstruction. In the first stage, a 2D convolutional network predicts damage masks on RGB slices extracted from a voxelized object, and these predictions are aggregated into a volumetric mask. In the second stage, a diffusion-based 3D U-Net performs mask-conditioned inpainting directly on voxel grids, reconstructing geometry and color while preserving observed regions. The model jointly predicts occupancy and color using a composite objective that combines occupancy reconstruction with masked color reconstruction and perceptual regularization. We evaluate the approach on a curated set of textured artifacts with synthetically generated damage using standard geometric and color metrics. Compared to symmetry-based baselines, our method produces more complete geometry and more coherent color reconstructions at a fixed 32^3 resolution. Overall, the results indicate that explicit mask conditioning is a practical way to guide volumetric diffusion models for joint 3D geometry and color inpainting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
