AI Paper Atlas

Research map / 3D vision / Face and shape

LHM: Large Animatable Human Reconstruction Model for Single Image to 3D in Seconds

Lingteng Qiu, Xiaodong Gu, Peihao Li, Qi Zuo, Weichao Shen, Junfei Zhang, Kejie Qiu, Weihao Yuan, Guanying Chen, Zilong Dong, Liefeng Bo

ICCV 2025 · 3D vision › Face and shape · approach: Full-body avatar reconstruction · 34 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 in-the-wild videos (all ~300K) to synthetic-only training (ablation)LHM-0.5B · Animation, in-the-wild videosPSNR: 19.753 -> 21.648Improved
increase video training data 10K to 100K (ablation)LHM-0.5B · Animation, in-the-wild videosPSNR: 20.692 -> 21.429Improved
increase video data from 100K to all (ablation)LHM-0.5B · Animation, in-the-wild videosLPIPS: 0.049 -> 0.044Improved
scale model from 0.5B to 1B parameters (ablation)LHM · Animation, in-the-wild videosPSNR: 21.648 -> 22.003Improved
scale model from 0.5B to 0.7B parameters (ablation)LHM · Animation, in-the-wild videosLPIPS: 0.044 -> 0.039Improved
use body-head transformer block instead of vanilla MM-Transformer (ablation)LHM-0.5B · Animation, in-the-wild videosPSNR: 20.072 -> 21.648Improved
use body-head transformer block instead of vanilla MM-Transformer (ablation)LHM-0.5B · Animation, in-the-wild videosLPIPS: 0.100 -> 0.044Improved
add head token shrinkage regularization (ablation)LHM-0.5B · Animation, in-the-wild videosPSNR: 21.037 -> 21.648Improved
add head token shrinkage regularization (ablation)LHM-0.5B · Animation, in-the-wild videosFC: 0.041 -> 0.042Hurt
add as-spherical-as-possible loss (ablation)LHM · QualitativeartifactsImproved
add as-close-as-possible loss (ablation)LHM · QualitativefloatersImproved
compare feed-forward LHM with AniGSLHM-0.5B · Animation, in-the-wild videosPSNR: 18.681 -> 21.648Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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