AI Paper Atlas

Research map / 3D vision / 3D generation

Generative Human Geometry Distribution

Xiangjun Tang, Biao Zhang, Peter Wonka

ICLR 2026 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 3 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 SMPL-based training pairs and distribution normalization instead of Gaussian source (ablation)Human geometry distribution · THuman2 dataset fittingChamfer distance: 0.0101 -> 0.0032Improved
add nearest-point training pair construction (ablation)Human geometry distribution · THuman2 dataset fittingChamfer distance: 0.0706 -> 0.0032Improved
add distribution normalization (zero-centered displacement field) (ablation)Human geometry distribution · THuman2 dataset fittingChamfer distance: 0.0071 -> 0.0032Improved
add distribution normalization (ablation)Human geometry distribution · single geometry fittingChamfer distance: 0.0020 -> 0.0032Hurt
sample SMPL points sparsely before nearest-point search instead of using the dense mesh (ablation)Training pair construction · THuman2 normal mapssampling completeness (qualitative)Improved
use auto-decoder instead of VecSet auto-encoder (ablation)Latent feature map encoding · THuman2Surface distance: 0.0018 -> 0.0012Improved
use a 2D feature map latent instead of independent embeddings in the auto-encoder (ablation)VecSet auto-encoder · THuman2Surface distance: 0.0018 -> 0.0014Improved
generate raw geometry directly with geometry distributions instead of rendering-enhanced baselinesHuman generation · THuman2 pose-conditioned generationFID: 42.90 -> 16.16 (raw); 17.43 -> 16.16 (vs enhanced gDNA)Improved
synthesize pose-aware feature maps for novel posesNovel pose generation · user study (25 participants)Plausibility (1-5): 2.66 -> 4.36Improved

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