TripoSR:從單張圖像快速進行3D物體重建
TripoSR: Fast 3D Object Reconstruction from a Single Image
March 4, 2024
作者: Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, Yan-Pei Cao
cs.AI
摘要
本技術報告介紹了 TripoSR,一個利用變壓器架構進行快速前向 3D 生成的 3D 重建模型,能夠從單張圖像中在 0.5 秒內生成 3D 網格。在 LRM 網絡架構的基礎上,TripoSR 整合了在數據處理、模型設計和訓練技術方面的重大改進。對公共數據集的評估顯示,與其他開源替代方案相比,TripoSR 在定量和定性上表現出優越性能。TripoSR 釋出於 MIT 授權下,旨在為研究人員、開發人員和創意人士提供最新的 3D 生成人工智能技術。
English
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.