TripoSR: Fast 3D Object Reconstruction from a Single Image

Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts +5 more
3/4/2024
cs.CV

No official code found. Best implementation: VAST-AI-Research/TripoSR (6,943 stars, MIT, last commit 2024-08-16).

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.

View on arXivView PDF

Code Implementations(1)

VAST-AI-Research/TripoSRCommunity100%
MIT

TripoSR: Fast 3D Object Reconstruction from a Single Image

6,943897PythonFeb 7, 20242 years agoMIT

Similar Papers

GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation

85% match1 repo6412024

ShapeGen: Towards High-Quality 3D Shape Synthesis

84% match2025

Array Camera Image Fusion using Physics-Aware Transformers

84% match1 repo52022

Home-made Diffusion Model from Scratch to Hatch

84% match2025

Training Transformers Together

83% match1 repo2.5k2022

MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers

83% match1 repo2.3k2024

Cite this paper

@article{tochilkin2024triposr,
  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},
  year   = {2024},
  eprint = {2403.02151},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2403.02151v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2403.02151.svg)](https://codeofpaper.com/paper/2403.02151)

Discussion