通过纹理引导的高斯-网格联合优化改进多视图重建
Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization
AI总结：
本文提出一种通过纹理引导的高斯-网格联合优化方法，实现多视图重建中几何与外观的统一优化，提升3D重建质量以支持后续编辑任务。
摘要：
从多视图图像中重建现实世界物体对于3D编辑、AR/VR和数字内容创作应用至关重要。现有方法通常优先考虑几何精度（多视图立体）或逼真渲染（新视图合成），往往将几何和外观优化分开，这阻碍了后续编辑任务。本文倡导对几何和外观优化进行统一处理，实现无缝的高斯-网格联合优化。更具体地说，我们提出了一种新的框架，通过高斯引导的网格可微渲染同时优化网格几何（顶点位置和面）和顶点颜色，利用输入图像的光度一致性以及法线和深度图的几何正则化。所获得的高质量3D重建可以进一步用于后续编辑任务，如重新照明和形状变形。我们的代码将在https://github.com/zhejia01/TexGuided-GS2Mesh上发布。
英文摘要：
Reconstructing real-world objects from multi-view images is essential for applications in 3D editing, AR/VR, and digital content creation. Existing methods typically prioritize either geometric accuracy (Multi-View Stereo) or photorealistic rendering (Novel View Synthesis), often decoupling geometry and appearance optimization, which hinders downstream editing tasks. This paper advocates an unified treatment on geometry and appearance optimization for seamless Gaussian-mesh joint optimization. More specifically, we propose a novel framework that simultaneously optimizes mesh geometry (vertex positions and faces) and vertex colors via Gaussian-guided mesh differentiable rendering, leveraging photometric consistency from input images and geometric regularization from normal and depth maps. The obtained high-quality 3D reconstruction can be further exploit in down-stream editing tasks, such as relighting and shape deformation. Our code will be released in https://github.com/zhejia01/TexGuided-GS2Mesh
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。
