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 highquality 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: optimizationbased and feed-forward (both single-view regression andmulti-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 UVstructured 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 largescale training. Experimental results demonstrate that our paradigm, powered by large-scale training, produces highquality 3D human Gaussians with intricate textures, facialdetails, and loose clothing deformation