Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cai, Zhejia, Jiang, Puhua, Mao, Shiwei, Cao, Hongkun, Huang, Ruqi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908865788903424
author Cai, Zhejia
Jiang, Puhua
Mao, Shiwei
Cao, Hongkun
Huang, Ruqi
author_facet Cai, Zhejia
Jiang, Puhua
Mao, Shiwei
Cao, Hongkun
Huang, Ruqi
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2511_03950
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization
Cai, Zhejia
Jiang, Puhua
Mao, Shiwei
Cao, Hongkun
Huang, Ruqi
Computer Vision and Pattern Recognition
Artificial Intelligence
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
title Improving Multi-View Reconstruction via Texture-Guided Gaussian-Mesh Joint Optimization
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.03950