TripoSR: Fast 3D Object Reconstruction from a Single Image

Authors:
  • DTDmitry Tochilkin
    Dmitry Tochilkin
  • DPDavid Pankratz
    David Pankratz
  • ZLZexiang Liu
    Zexiang Liu
  • ZHZixuan Huang
    Zixuan Huang
  • ALAdam Letts
    Adam Letts
  • YLYangguang Li
    Yangguang Li
  • DLDing Liang
    Ding Liang
  • CLChristian Laforte
    Christian Laforte
  • VJVarun Jampani
    Varun Jampani
  • YCYan-Pei Cao
    Yan-Pei Cao
Preprint
Publisher website
Google Scholar
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.
All Related Versions