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
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 3D Shape Reconstruction | OmniObject3D | CD0.048 | 17 | |
| Single-view 3D Reconstruction | GSO (test) | CD0.145 | 13 | |
| 3D Reconstruction Rendering | GSO | PSNR16.445 | 10 | |
| 3D Shape Reconstruction | GSO | FS0.896 | 10 | |
| Single-view 3D Reconstruction | OmniObject3D | Chamfer Distance (CD)0.144 | 8 | |
| 3D Object Reconstruction | GSO | CD0.111 | 7 | |
| 3D Object Reconstruction | OmniObject3D | Chamfer Distance (CD)0.103 | 7 | |
| Text-to-3D Generation | Dreamfusion gallery 50 prompts | PSNR23.76 | 7 | |
| 3D Reconstruction | OmniObject3D (1700 unseen samples) | CLIP Score0.664 | 7 | |
| Image-to-3D Generation | Google Scanned Objects (GSO) | CLIP Similarity47.8 | 7 |
Showing 10 of 15 rows