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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add in-the-wild videos (all ~300K) to synthetic-only training (ablation) | LHM-0.5B · Animation, in-the-wild videos | PSNR: 19.753 -> 21.648 | Improved |
| increase video training data 10K to 100K (ablation) | LHM-0.5B · Animation, in-the-wild videos | PSNR: 20.692 -> 21.429 | Improved |
| increase video data from 100K to all (ablation) | LHM-0.5B · Animation, in-the-wild videos | LPIPS: 0.049 -> 0.044 | Improved |
| scale model from 0.5B to 1B parameters (ablation) | LHM · Animation, in-the-wild videos | PSNR: 21.648 -> 22.003 | Improved |
| scale model from 0.5B to 0.7B parameters (ablation) | LHM · Animation, in-the-wild videos | LPIPS: 0.044 -> 0.039 | Improved |
| use body-head transformer block instead of vanilla MM-Transformer (ablation) | LHM-0.5B · Animation, in-the-wild videos | PSNR: 20.072 -> 21.648 | Improved |
| use body-head transformer block instead of vanilla MM-Transformer (ablation) | LHM-0.5B · Animation, in-the-wild videos | LPIPS: 0.100 -> 0.044 | Improved |
| add head token shrinkage regularization (ablation) | LHM-0.5B · Animation, in-the-wild videos | PSNR: 21.037 -> 21.648 | Improved |
| add head token shrinkage regularization (ablation) | LHM-0.5B · Animation, in-the-wild videos | FC: 0.041 -> 0.042 | Hurt |
| add as-spherical-as-possible loss (ablation) | LHM · Qualitative | artifacts | Improved |
| add as-close-as-possible loss (ablation) | LHM · Qualitative | floaters | Improved |
| compare feed-forward LHM with AniGS | LHM-0.5B · Animation, in-the-wild videos | PSNR: 18.681 -> 21.648 | Improved |
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.
- AniGS — AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction (CVPR 2025) · better on 4 of 4 shared results
- PSHuman — PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025) · better on 4 of 4 shared results
- DreamGaussian — DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation (ICLR 2024) · better on 4 of 4 shared results
- En3D — En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data (CVPR 2024) · better on 1 of 1 shared result
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
- IDOL: Instant Photorealistic 3D Human Creation from a Single Image (CVPR 2025 · similarity 0.88)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.87)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.87)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.87)
- LRM: Large Reconstruction Model for Single Image to 3D (ICLR 2024 · similarity 0.87)
- GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data (NeurIPS 2025 · similarity 0.87)
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.
