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:
this https URL

提出了 MeshLRM，一种基于 LRM 的新方法，在不到一秒的时间内仅使用四个输入图像进行高质量网格的重建。与以往的大型重建模型（LRMs）不同，MeshLRM 在 LRM 框架中融入了可微分网格提取和渲染，可通过微调预训练的 NeRF LRM 进行端到端的网格重建。此外，通过简化先前 LRMs 中的多个复杂设计，我们改进了 LRM 架构。MeshLRM 的 NeRF 初始化使用低分辨率和高分辨率图像进行顺序训练；这种新的 LRM 训练策略实现了显著更快的收敛速度，从而在更少的计算量下获得更好的质量。我们的方法在稀疏视图输入下实现了最先进的网格重建，并且还可应用于很多下游应用，包括文本到三维和单图像到三维的生成。项目页面：此链接。