Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization
This work addresses the challenge of decoupling geometry and appearance optimization in multi-view reconstruction, which is important for applications in 3D editing, AR/VR, and digital content creation, representing an incremental improvement over existing methods.
The paper tackles the problem of reconstructing real-world objects from multi-view images by proposing a unified framework that simultaneously optimizes mesh geometry and vertex colors using Gaussian-guided mesh differentiable rendering, achieving high-quality 3D reconstructions suitable for editing tasks like relighting and shape deformation.
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. The code will be publicly available upon acceptance.