Research map / 3D vision / Face and shape
Clothed human modeling
Models and reconstructs clothing and clothed bodies using implicit surfaces and template decomposition.
60 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2019–2026) · an approach in Face and shape, keyword cluster “avatar · human · body”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
26 papers in 2023–24 and 13 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 7.2% to 3.6%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2019 · SiCloPe: Silhouette-Based Clothed People (CVPR 2019 · 214 citations)
- 2020 · Learning to Dress 3D People in Generative Clothing (CVPR 2020 · 373 citations)
- 2021 · SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks (CVPR 2021 · 223 citations)
- 2022 · ICON: Implicit Clothed Humans Obtained From Normals (CVPR 2022 · 313 citations)
- 2023 · ECON: Explicit Clothed Humans Optimized via Normal Integration (CVPR 2023 · 195 citations)
- 2024 · SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · 57 citations)
- 2025 · DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · 4 citations)
- 2026 · HumanPro: Single-view 3D Clothed Human Reconstruction with Progressive Normal Guidance (AAAI 2026 · 5 citations)
Earliest papers here
- SiCloPe: Silhouette-Based Clothed People (CVPR 2019 · 214 citations)
- SimulCap : Single-View Human Performance Capture With Cloth Simulation (CVPR 2019 · 109 citations)
- Learning to Dress 3D People in Generative Clothing (CVPR 2020 · 373 citations)
What has been tried
51 papers here report 482 measured changes (a component added, removed or swapped, compared with a baseline): helped 79%, no clear effect 4%, hurt 15%, mixed 2%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add cross-attention instead of omitting it | CAPE-NFP · Chamfer | 0.9846 -> 0.7725 | Helped | SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · 57 citations) |
| Add optical flow labels to PAR | CLOTH4D Outer · mean accuracy | 0.714 -> 0.942 | Helped | 4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations (CVPR 2024 · 30 citations) |
| Add a control cage to pattern optimization | Dress, against GT Scan · CD | 3.866 -> 1.122 | Helped | DiffAvatar: Simulation-Ready Garment Optimization with Differentiable Simulation (CVPR 2024 · 29 citations) |
| add canonical-space SDS | CAPE · IoU | 79.97% -> 82.89% | Helped | GALA: Generating Animatable Layered Assets from a Single Scan (CVPR 2024 · 17 citations) |
| add progressive HF SDF rather than vanilla SDF | CAPE · Chamfer distance | 0.8118 -> 0.7430 | Helped | HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 2024 · 15 citations) |
| Add style consistency loss to L1 loss | 2K2K · PSNR | 18.427 -> 24.476 | Helped | Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field (CVPR 2024 · 13 citations) |
| add partial texture input to TexFeatNet | DynaCap S1 novel pose · PSNR | 26.44 -> 30.24 | Helped | Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras (CVPR 2024 · 10 citations) |
| add RefineVS to the StretchVS-only model | THuman 2.0 · Chamfer distance (cm) | 0.979 -> 0.628 | Helped | VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · 8 citations) |
| Add ECON initialization | Lab (average over 3 sequences) · PSNR | 26.63 -> 32.03 | Helped | DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · 6 citations) |
| use part-based parameterization instead of direct PCA shape parameters | SSP-3D test · PVE-T-SC (mm) | 12.3 -> 11.4 | Helped | ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation (AAAI 2024 · 5 citations) |
| add cloth and body template regularization losses | 4D-DRESS (cloth) · CD | 8.245 -> 3.902 | Helped | DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · 4 citations) |
| Add PBR shading to 3DGS-only rendering | Novel poses (4 video sequences) · FSIM | 0.825 -> 0.834 | Helped | PGC: Physics-Based Gaussian Cloth from a Single Pose (CVPR 2025 · 4 citations) |
What reviewers will expect
Datasets and baselines named in the 7 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- DeepFashion · 2 of 7 papers
- THuman2.0 · 2 of 7 papers
Baselines
- PIFu · 2 of 7 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 39 papers; from OpenAlex and the papers' affiliations).
- Max Planck Institute for Intelligent Systems · 3 papers
- Wuhan University · 2 papers
- Nanyang Technological University · 2 papers
- South China University of Technology · 2 papers
- Meta · 2 papers
- Seoul National University · 2 papers
- Zhejiang University · 2 papers
Use it
Download BibTeX of 39 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Gaussian and implicit head avatars (115 papers)
- Full-body avatar reconstruction (78 papers)
- Generative textures for 3D humans (27 papers)
Elsewhere in the topic
- Neural implicit surface reconstruction (131 papers)
- Textured mesh generation (111 papers)
- Primitive-based shape abstraction (99 papers)
- Single-view 3D reconstruction (96 papers)
- Face reflectance and relightable rendering (85 papers)
- 3D morphable face model regression (80 papers)
- Articulated and non-rigid shape learning (75 papers)
- 3D shape generative modeling (74 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).