Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

TripoSR: Fast 3D Object Reconstruction from a Single Image

About

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.

Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, Yan-Pei Cao• 2024

Related benchmarks

TaskDatasetResultRank
RoutingGSO novel objects {c ∈ C0}
Regret1.8041
24
3D Shape ReconstructionOmniObject3D
CD0.048
17
3D GenerationToys4k
CLIP Score83.14
16
3D GenerationUniLat1K
CLIP Score83.37
16
Image-to-3D GenerationGoogle Scanned Objects (GSO)
CLIP Similarity71.46
14
Single-view 3D ReconstructionGSO (test)
CD0.145
13
RoutingGSO (novel objects)
Regret2.5109
11
3D Reconstruction RenderingGSO
PSNR16.445
10
3D Shape ReconstructionGSO
FS0.896
10
Single-view 3D ReconstructionOmniObject3D
Chamfer Distance (CD)0.144
8
Showing 10 of 20 rows

Other info

Follow for update