AI Paper Atlas

Research map / 3D vision / Face and shape

MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos

Daisheng Jin, Ying He

AAAI 2026 · 3D vision › Face and shape · approach: Clothed human modeling · 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
add CloSim motion offsets on top of LBS (ablation)MonoCloth · NeuMan (4 sequences)PSNR: 31.93 -> 33.53Improved
add CloSim motion offsets on top of LBS (ablation)MonoCloth · NeuMan (4 sequences)LPIPS (x10^-2): 1.40 -> 1.20Improved
add temporal multi-frame sampling (ablation)MonoCloth · NeuMan (4 sequences)PSNR: 33.00 -> 33.53Improved
add temporal multi-frame sampling (ablation)MonoCloth · NeuMan (4 sequences)LPIPS (x10^-2): 1.29 -> 1.20Improved
add geometry loss (ablation)MonoCloth · NeuMan (4 sequences)PSNR: 32.55 -> 33.53Improved
add geometry loss (ablation)MonoCloth · NeuMan (4 sequences)LPIPS (x10^-2): 1.30 -> 1.20Improved
add geometry loss (ablation)MonoCloth · NeuMan (4 sequences)SSIM: 0.985 -> 0.986Improved
add monocular-video pretraining on five X-Humans subjects (ablation)MonoCloth · NeuMan (4 sequences)PSNR: 33.18 -> 33.53Improved
add monocular-video pretraining on five X-Humans subjects (ablation)MonoCloth · NeuMan (4 sequences)LPIPS (x10^-2): 1.28 -> 1.20Improved
use MonoCloth instead of ExAvatarExAvatar · X-HumansPSNR: 29.41 -> 30.68Improved
use MonoCloth without pretraining instead of pretrained Vid2Avatar-ProVid2Avatar-Pro · NeuMan (4 sequences)LPIPS (x10^-2): 1.19 -> 1.28Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 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