AI Paper Atlas

Research map / 3D vision / 3D generation

SIGMAN: Scaling 3D Human Gaussian Generation with Millions of Assets

Yuhang Yang, Fengqi Liu, Yixing Lu, Qin Zhao, Pingyu Wu, Wei Zhai, Ran Yi, Yang Cao, Lizhuang Ma, Zheng-Jun Zha, Junting Dong

ICCV 2025 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use UV-structured latent tokens vs explicit SMPL-X point prior in VAE (ablation)SIGMAN VAE · HGS-1M VAE reconstructionPSNR: 28.61 -> 29.32Improved
add Conv-Atten dual branch (ablation)SIGMAN VAE · HGS-1M VAE ablationPSNR: 29.04 -> 29.32Improved
add UV-map initialization of learnable tokens (ablation)SIGMAN VAE · HGS-1M VAE ablationPSNR: 28.92 -> 29.32Improved
increase VAE latent channels from 16 to 32 (ablation)SIGMAN VAE · HGS-1M VAE ablationPSNR: 29.32 -> 29.78 (VAE); generation harderMixed
increase VAE latent channels from 4 to 16 (ablation)SIGMAN VAE · HGS-1M VAE ablationPSNR: 25.14 -> 29.32Improved
scale the VAE up from 146M (ablation)SIGMAN VAE · HGS-1M VAE ablationPSNR: 29.14 -> 29.32Improved
use MM-DiT instead of Cross-DiT (ablation)SIGMAN generation · HGS-1M image-to-3DPSNR: 24.72 -> 25.45Improved
use Sapiens human encoder instead of CLIP or DINOv2 (ablation)SIGMAN generation · HGS-1M image-to-3DPSNR: 24.07 -> 25.45 (CLIP); 24.95 -> 25.45 (DINOv2)Improved
use rectified flow instead of DDPM v-prediction (ablation)SIGMAN generation · HGS-1M image-to-3DPSNR: 25.45 vs 25.38No clear effect
scale DiT from 200M to 2B (ablation)SIGMAN generation · HGS-1M image-to-3DPSNR: 23.73 -> 24.70 -> 25.45Improved
train on the whole HGS-1M dataset vs 300k subsetSIGMAN · HGS-1M image-to-3DPSNR: 25.45 -> 26.14Improved
latent generation with UV VAE and MM-DiT vs optimization, cascade and regression baselinesSIGMAN · HGS-1M image-to-3DPSNR: 21.03 -> 25.45Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy