TripoSR: Fast 3D Object Reconstruction from a Single Image

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tochilkin, Dmitry, Pankratz, David, Liu, Zexiang, Huang, Zixuan, Letts, Adam, Li, Yangguang, Liang, Ding, Laforte, Christian, Jampani, Varun, Cao, Yan-Pei
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866907819795546112
author Tochilkin, Dmitry
Pankratz, David
Liu, Zexiang
Huang, Zixuan
Letts, Adam
Li, Yangguang
Liang, Ding
Laforte, Christian
Jampani, Varun
Cao, Yan-Pei
author_facet Tochilkin, Dmitry
Pankratz, David
Liu, Zexiang
Huang, Zixuan
Letts, Adam
Li, Yangguang
Liang, Ding
Laforte, Christian
Jampani, Varun
Cao, Yan-Pei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02151
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TripoSR: Fast 3D Object Reconstruction from a Single Image
Tochilkin, Dmitry
Pankratz, David
Liu, Zexiang
Huang, Zixuan
Letts, Adam
Li, Yangguang
Liang, Ding
Laforte, Christian
Jampani, Varun
Cao, Yan-Pei
Computer Vision and Pattern Recognition
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.
title TripoSR: Fast 3D Object Reconstruction from a Single Image
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.02151