Research map / 3D vision / Face and shape
Articulated and non-rigid shape learning
Learns deformable and articulated shapes and dense correspondence from casual videos and image collections.
75 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Face and shape, keyword cluster “3d shape · shapes · object”
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.
20 papers in 2023–24 and 13 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 5.5% 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
- 2016 · Consensus of Non-Rigid Reconstructions (CVPR 2016 · 50 citations)
- 2017 · 3D Menagerie: Modeling the 3D Shape and Pose of Animals (CVPR 2017 · 388 citations)
- 2018 · Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction (CVPR 2018 · 217 citations)
- 2019 · Unsupervised Learning of Dense Shape Correspondence (CVPR 2019 · 170 citations)
- 2020 · Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the Wild (CVPR 2020 · 246 citations)
- 2021 · LASR: Learning Articulated Shape Reconstruction From a Monocular Video (CVPR 2021 · 81 citations)
- 2022 · BANMo: Building Animatable 3D Neural Models From Many Casual Videos (CVPR 2022 · 125 citations)
- 2023 · MagicPony: Learning Articulated 3D Animals in the Wild (CVPR 2023 · 57 citations)
- 2024 · Learning the 3D Fauna of the Web (CVPR 2024 · 23 citations)
- 2025 · GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction (CVPR 2025 · 3 citations)
- 2026 · Kinematics-Driven Gaussian Shape Deformation for Blurry Monocular Dynamic Scenes (ICML 2026 · 0 citations)
Earliest papers here
- Consensus of Non-Rigid Reconstructions (CVPR 2016 · 50 citations)
- Inextensible Non-Rigid Shape-From-Motion by Second-Order Cone Programming (CVPR 2016 · 30 citations)
- Isometric Non-Rigid Shape-From-Motion in Linear Time (CVPR 2016 · 29 citations)
What has been tried
63 papers here report 627 measured changes (a component added, removed or swapped, compared with a baseline): helped 70%, no clear effect 7%, hurt 18%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add a Semantic Bank of Skinned Models | Animal reconstruction · 3D shape plausibility | Helped | Learning the 3D Fauna of the Web (CVPR 2024 · 23 citations) | |
| Add deformation-model fine-tuning and vertex-position optimization | CLOTH3D test skirts, GT normals · CD (×103) | 2.04 -> 1.67 | Helped | Garment Recovery with Shape and Deformation Priors (CVPR 2024 · 15 citations) |
| remove depth supervision | Pascal horse, cow, and sheep; CUB bird · PCK@0.1 | 42.4, 30.1, 26.8, 49.9 -> 44.9, 33.6, 29.1, 51.9 | Helped | SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · 9 citations) |
| Use voting-based rather than SVD-based projection | VR-Folding Pants Folding · Dchamf | 1.53 -> 0.99 | Helped | GaPT-DAR: Category-level Garments Pose Tracking via Integrated 2D Deformation and 3D Reconstruction (CVPR 2025 · 3 citations) |
| replace selecting OBB edges with absolute continuous joint-position regression | 6-15 parts · position error | 0.03 -> 0.7 | Hurt | Real2Code: Reconstruct Articulated Objects via Code Generation (ICLR 2025 · 1 citation) |
| add the full spatial-weighted nuclear norm (SWNN) module | MoCap: Drink, Pickup, Yoga, Stretch, Dance, Face; NRSfM Challenge: Articulated (circle), Articulated (flyby), Stretch (zigzag) · 3D reconstruction error | 0.0050 -> 0.0031; 0.0137 -> 0.0126; 0.0120 -> 0.0109; 0.0132 -> 0.0114; 0.0932 -> 0.0921; 0.0161 -> 0.0144; 3.5626 -> 2. | Helped | Non-Rigid Structure-from-Motion: Temporally-Smooth Procrustean Alignment and Spatially-Variant Deformation Modeling (CVPR 2024 · 1 citation) |
| Represent shapes with Jacobian fields instead of vertex coordinates | ormthings · FID (×10^-2) | 3.52 -> 1.17 | Helped | Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses (NeurIPS 2024 · 1 citation) |
| Remove DINO feature loss during the motion and fine shape phase | motion and fine shape phase · shape detail | Helped | S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video (ICML 2024 · 0 citations) |
What reviewers will expect
Datasets and baselines named in the 11 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- CLOTH3D · 3 of 11 papers
- Animal3D · 3 of 11 papers
- PASCAL VOC · 2 of 11 papers
- VR-Folding · 2 of 11 papers
Baselines
- MagicPony · 3 of 11 papers
- UMR · 2 of 11 papers
- A-CSM · 2 of 11 papers
- Hi-LASSIE · 2 of 11 papers
- GarmentNets · 2 of 11 papers
- GarmentTracking · 2 of 11 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 33 papers; from OpenAlex and the papers' affiliations).
- Google · 3 papers
- Waymo · 2 papers
- University of Oxford · 2 papers
- EPFL · 2 papers
- Stanford University · 2 papers
Use it
Download BibTeX of 40 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
- Primitive-based shape abstraction (99 papers)
- Single-view 3D reconstruction (96 papers)
- 3D shape generative modeling (74 papers)
- Optimization-based shape matching (59 papers)
Elsewhere in the topic
- Neural implicit surface reconstruction (131 papers)
- Gaussian and implicit head avatars (115 papers)
- Textured mesh generation (111 papers)
- Face reflectance and relightable rendering (85 papers)
- 3D morphable face model regression (80 papers)
- Full-body avatar reconstruction (78 papers)
- Learned mesh and geometric representations (73 papers)
- Clothed human modeling (60 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).