English

TripoSR: Fast 3D Object Reconstruction from a Single Image

Computer Vision and Pattern Recognition 2024-03-05 v1

Abstract

This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0.5 seconds. Building upon the LRM network architecture, TripoSR integrates substantial improvements in data processing, model design, and training techniques. Evaluations on public datasets show that TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives. Released under the MIT license, TripoSR is intended to empower researchers, developers, and creatives with the latest advancements in 3D generative AI.

Keywords

Cite

@article{arxiv.2403.02151,
  title  = {TripoSR: Fast 3D Object Reconstruction from a Single Image},
  author = {Dmitry Tochilkin and David Pankratz and Zexiang Liu and Zixuan Huang and Adam Letts and Yangguang Li and Ding Liang and Christian Laforte and Varun Jampani and Yan-Pei Cao},
  journal= {arXiv preprint arXiv:2403.02151},
  year   = {2024}
}

Comments

Model: https://huggingface.co/stabilityai/TripoSR Code: https://github.com/VAST-AI-Research/TripoSR Demo: https://huggingface.co/spaces/stabilityai/TripoSR

R2 v1 2026-06-28T15:08:32.432Z