arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02151cs.CV
收藏

TripoSR:基于单张图像的快速3D物体重建

TripoSR: Fast 3D Object Reconstruction from a Single Image

Stability AI;Tripo AI

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

AI总结:

本文提出基于transformer的前馈3D重建模型TripoSR,可在0.5秒内由单图生成3D网格,并通过改进LRM架构在公开数据集上超越开源替代方案。

摘要:

本技术报告介绍了TripoSR,这是一个利用transformer架构实现快速前馈3D生成的3D重建模型,可在0.5秒内根据单张图像生成3D网格。TripoSR以LRM网络架构为基础,在数据处理、模型设计和训练技术方面融入了大量改进。在公开数据集上的评估表明,与其他开源替代方案相比,TripoSR在定量和定性方面均表现出更优性能。TripoSR以MIT许可证发布,旨在为研究人员、开发者和创意工作者提供3D生成式AI的最新进展。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑