We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on NeRF-based reconstruction, MeshLRM incorporates differentiable mesh extraction and rendering within the LRM framework. This allows for end-to-end mesh reconstruction by fine-tuning a pre-trained NeRF LRM with mesh rendering. Moreover, we improve the LRM architecture by simplifying several complex designs in previous LRMs. MeshLRM's NeRF initialization is sequentially trained with low- and high-resolution images; this new LRM training strategy enables significantly faster convergence and thereby leads to better quality with less compute. Our approach achieves state-of-the-art mesh reconstruction from sparse-view inputs and also allows for many downstream applications, including text-to-3D and single-image-to-3D generation. Project page: https://sarahweiii.github.io/meshlrm/
@article{arxiv.2404.12385,
title = {MeshLRM: Large Reconstruction Model for High-Quality Meshes},
author = {Xinyue Wei and Kai Zhang and Sai Bi and Hao Tan and Fujun Luan and Valentin Deschaintre and Kalyan Sunkavalli and Hao Su and Zexiang Xu},
journal= {arXiv preprint arXiv:2404.12385},
year = {2025}
}