AI Paper Atlas

Research map / 3D vision / Face and shape

HumanLiff: Layer-wise 3D Human Diffusion Model

Shoukang Hu, Fangzhou Hong, Tao Hu, Liang Pan, Haiyi Mei, Weiye Xiao, Lei Yang, Ziwei Liu

IJCV 2025 · 3D vision › Face and shape · approach: Clothed human modeling · 23 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
add 3D condition UNet encoder instead of AdaGN (ablation)HumanLiff · SynBody layer-wise (Layer 1)FID: 28.37 -> 25.09Improved
add 3D condition UNet encoder instead of AdaGN (ablation)HumanLiff · SynBody layer-wise (Layer 1)L-PSNR: 20.96 -> 28.14Improved
add 3D condition UNet encoder instead of AdaGN (ablation)HumanLiff · SynBody layer-wise (Layer 3)L-PSNR: 22.93 -> 29.87Improved
add 3D condition UNet encoder instead of cross-attention (ablation)HumanLiff · SynBody layer-wise (Layer 0)FID: 26.62 -> 22.28Improved
add 3D condition UNet encoder instead of cross-attention (ablation)HumanLiff · SynBody layer-wise (Layer 1)L-PSNR: 27.18 -> 28.14Improved
add 3D condition UNet encoder instead of cross-attention (ablation)HumanLiff · SynBody layer-wise (Layer 3)FID: 27.94 -> 25.20Improved
add tri-plane shift (ablation)layer-wise tri-plane fitting · SynBody tri-plane fittingPSNR: 31.35 -> 31.97Improved
add tri-plane shift (ablation)layer-wise tri-plane fitting · SynBody tri-plane fittingLPIPS: 0.05 -> 0.04Improved
add tri-plane shift (ablation)layer-wise tri-plane fitting · SynBody tri-plane fittingSSIM: 0.97 -> 0.98Improved
add AdaGN conditioning on 1D latent (Rodin) in place of 3D UNet encoder (ablation)Rodin vs HumanLiff · SynBody layer-wise (Layer 1)L-PSNR: 28.14 -> 19.54Hurt

Later papers that compared with this method

1 later accepted paper reports HumanLiff as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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