Previous efforts have managed to generate production-ready 3D assets from text or images. However, these methods primarily employ NeRF or 3D Gaussian representations, which are not adept at producing smooth, high-quality geometries required by modern rendering pipelines. In this paper, we propose LDM, a novel feed-forward framework capable of generating high-fidelity, illumination-decoupled textured mesh from a single image or text prompts. We firstly utilize a multi-view diffusion model to generate sparse multi-view inputs from single images or text prompts, and then a transformer-based model is trained to predict a tensorial SDF field from these sparse multi-view image inputs. Finally, we employ a gradient-based mesh optimization layer to refine this model, enabling it to produce an SDF field from which high-quality textured meshes can be extracted. Extensive experiments demonstrate that our method can generate diverse, high-quality 3D mesh assets with corresponding decomposed RGB textures within seconds.
@article{arxiv.2405.14580,
title = {LDM: Large Tensorial SDF Model for Textured Mesh Generation},
author = {Rengan Xie and Wenting Zheng and Kai Huang and Yizheng Chen and Qi Wang and Qi Ye and Wei Chen and Yuchi Huo},
journal= {arXiv preprint arXiv:2405.14580},
year = {2024}
}