ExMesh++：通过拓扑自适应重建与分解从多视图图像生成可重光照UV-PBR网格资产
ExMesh++: From Multi-View Images to Relightable UV-PBR Mesh Assets via Topology-Adaptive Reconstruction and Decomposition
浏览论文内容
中文总结 AI 辅助
ExMesh++是一种分阶段框架，通过拓扑自适应重建与分解，从多视图图像生成可重光照UV-PBR网格资产，在几何精度、重光照性能上表现优异，导出资产可直接用于标准DCC工作流。
中文摘要 AI 辅助
多视图重建已从表面恢复延伸至可编辑且可重光照的网格资产，此类资产需具备良好的拓扑结构、有效的UV参数化及明确的PBR材质贴图。现有表面重建方法优化隐式场、高斯基元或其他中间表示，将其转换为上述资产常需表面提取与纹理烘焙；逆渲染方法虽能估计材质与光照，但这些组件往往仍绑定于神经场或基于点的基元，而非最终网格。几何、材质与光照的联合优化可能使各变量相互补偿，导致分解模糊。为解决这些局限，本文提出ExMesh++——一种从多视图图像重建可重光照UV-PBR网格资产的分阶段框架：第一阶段通过自适应顶点分裂与合并优化显式网格几何与拓扑，同时在拓扑变化时保持UV一致性；第二阶段固定生成的网格-UV载体，优化UV空间PBR贴图及环境光照。基于该稳定载体，ExMesh++通过使用共享UV-PBR材质的次光线追踪建模一次漫反射间接光照。实验表明，该方法具备有竞争力的几何精度、出色的重光照性能，且导出资产可直接用于标准DCC工作流。
英文摘要
Multi-view reconstruction extends beyond surface recovery to editable and relightable mesh assets. Such assets require well-formed topology, valid UV parameterization, and explicit PBR material maps. Existing surface reconstruction approaches optimize implicit fields, Gaussian primitives, or other intermediate representations. Converting them into such assets often requires surface extraction and texture baking. Inverse-rendering methods estimate materials and illumination, yet these components often remain tied to neural fields or point-based primitives rather than the final mesh. Joint optimization of geometry, materials, and lighting may also allow these variables to compensate for one another, leading to ambiguous decomposition. To address these limitations, we present ExMesh++, a staged framework for reconstructing relightable UV-PBR mesh assets from multi-view images. The first stage refines explicit mesh geometry and topology through adaptive vertex splitting and merging, while maintaining UV consistency as the topology changes. The second stage fixes the resulting mesh-UV carrier and optimizes UV-space PBR maps together with environment lighting. Building on this stable carrier, ExMesh++ models one-bounce diffuse indirect illumination through secondary-ray tracing with shared UV-PBR materials. Experiments demonstrate competitive geometry accuracy, strong relighting performance, and direct usability of the exported assets in standard DCC workflows.
发表机构
- University of Science and Technology of China（中国科学技术大学）
- Alibaba Group（阿里巴巴集团）
机构由 AI 辅助整理，请以论文原文为准。
