Research map / 3D vision / Face and shape
MonoCloth: Reconstruction and Animation of Cloth-Decoupled Human Avatars from Monocular Videos
Daisheng Jin, Ying He
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 CloSim motion offsets on top of LBS (ablation) | MonoCloth · NeuMan (4 sequences) | PSNR: 31.93 -> 33.53 | Improved |
| add CloSim motion offsets on top of LBS (ablation) | MonoCloth · NeuMan (4 sequences) | LPIPS (x10^-2): 1.40 -> 1.20 | Improved |
| add temporal multi-frame sampling (ablation) | MonoCloth · NeuMan (4 sequences) | PSNR: 33.00 -> 33.53 | Improved |
| add temporal multi-frame sampling (ablation) | MonoCloth · NeuMan (4 sequences) | LPIPS (x10^-2): 1.29 -> 1.20 | Improved |
| add geometry loss (ablation) | MonoCloth · NeuMan (4 sequences) | PSNR: 32.55 -> 33.53 | Improved |
| add geometry loss (ablation) | MonoCloth · NeuMan (4 sequences) | LPIPS (x10^-2): 1.30 -> 1.20 | Improved |
| add geometry loss (ablation) | MonoCloth · NeuMan (4 sequences) | SSIM: 0.985 -> 0.986 | Improved |
| add monocular-video pretraining on five X-Humans subjects (ablation) | MonoCloth · NeuMan (4 sequences) | PSNR: 33.18 -> 33.53 | Improved |
| add monocular-video pretraining on five X-Humans subjects (ablation) | MonoCloth · NeuMan (4 sequences) | LPIPS (x10^-2): 1.28 -> 1.20 | Improved |
| use MonoCloth instead of ExAvatar | ExAvatar · X-Humans | PSNR: 29.41 -> 30.68 | Improved |
| use MonoCloth without pretraining instead of pretrained Vid2Avatar-Pro | Vid2Avatar-Pro · NeuMan (4 sequences) | LPIPS (x10^-2): 1.19 -> 1.28 | Hurt |
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.
- 3DGS-Avatar — 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024) · better on 3 of 3 shared results
- GaussianAvatar — GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (CVPR 2024) · better on 3 of 3 shared results
- InstantAvatar — InstantAvatar: Learning Avatars From Monocular Video in 60 Seconds (CVPR 2023) · better on 3 of 3 shared results
- Vid2Avatar — Vid2Avatar: 3D Avatar Reconstruction From Videos in the Wild via Self-Supervised Scene Decomposition (CVPR 2023) · better on 3 of 3 shared results
- HumanNeRF — HumanNeRF: Efficiently Generated Human Radiance Field From Sparse Inputs (CVPR 2022) · better on 3 of 3 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
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.91)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.90)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.90)
- IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (CVPR 2024 · similarity 0.89)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · similarity 0.88)
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.
