SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets
SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets
3D human digitization has long been a highly pursued yet challenging task. Existing methods aim to generate high-quality 3D digital humans from single or multiple views, but remain primarily constrained by current paradigms and the scarcity of 3D human assets. Specifically, recent approaches fall into several paradigms: optimization-based and feed-forward (both single-view regression and multi-view generation with reconstruction). However, they are limited by slow speed, low quality, cascade reasoning, and ambiguity in mapping low-dimensional planes to high-dimensional space due to occlusion and invisibility, respectively. Furthermore, existing 3D human assets remain small-scale, insufficient for large-scale training. To address these challenges, we propose a latent space generation paradigm for 3D human digitization, which involves compressing multi-view images into Gaussians via a UV-structured VAE, along with DiT-based conditional generation, we transform the ill-posed low-to-high-dimensional mapping problem into a learnable distribution shift, which also supports end-to-end inference. In addition, we employ the multi-view optimization approach combined with synthetic data to construct the HGS-1M dataset, which contains $1$ million 3D Gaussian assets to support the large-scale training. Experimental results demonstrate that our paradigm, powered by large-scale training, produces high-quality 3D human Gaussians with intricate textures, facial details, and loose clothing deformation.
Yuhang Yang、Fengqi Liu、Yixing Lu、Qin Zhao、Pingyu Wu、Wei Zhai、Ran Yi、Yang Cao、Lizhuang Ma、Zheng-Jun Zha、Junting Dong
计算技术、计算机技术
Yuhang Yang,Fengqi Liu,Yixing Lu,Qin Zhao,Pingyu Wu,Wei Zhai,Ran Yi,Yang Cao,Lizhuang Ma,Zheng-Jun Zha,Junting Dong.SIGMAN:Scaling 3D Human Gaussian Generation with Millions of Assets[EB/OL].(2025-04-09)[2025-05-06].https://arxiv.org/abs/2504.06982.点此复制
评论