Research map / 3D vision / Human pose estimation

Human mesh recovery from images

Recovers 3D body meshes end-to-end with pose calibration, point guidance and diffusion.

58 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Human pose estimation, keyword cluster “body · motion · human mesh”

State History Benchmarks Tried Baselines Checklist Preprints Who Export

How it got here

Most cited paper of each year

• 2018 · End-to-End Recovery of Human Shape and Pose (CVPR 2018 · 1,958 citations)
• 2021 · End-to-End Human Pose and Mesh Reconstruction with Transformers (CVPR 2021 · 707 citations)
• 2022 · Putting People in Their Place: Monocular Regression of 3D People in Depth (CVPR 2022 · 162 citations)
• 2023 · One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer (CVPR 2023 · 116 citations)
• 2024 · TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation (CVPR 2024 · 70 citations)
• 2025 · PromptHMR: Promptable Human Mesh Recovery (CVPR 2025 · 26 citations)
• 2026 · FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery (NeurIPS 2026 · 0 citations)

Earliest papers here

• End-to-End Recovery of Human Shape and Pose (CVPR 2018 · 1,958 citations)
• End-to-End Human Pose and Mesh Reconstruction with Transformers (CVPR 2021 · 707 citations)
• AGORA: Avatars in Geography Optimized for Regression Analysis (CVPR 2021 · 197 citations)

Benchmark records

The best number each year that beat every earlier one, among papers of this approach reporting their own method. Numbers are extracted by AI from each paper's text; check the paper before citing.

What has been tried

45 papers here report 487 measured changes (a component added, removed or swapped, compared with a baseline): helped 82%, no clear effect 4%, hurt 13%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

Baseline numbers that disagree

The same baseline on the same benchmark and metric, reported more than 5% apart by different papers here. Training budgets, data splits and reimplementations differ, so state which number you compare with.

What reviewers will expect

Datasets and baselines named in the 11 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.

Recent preprints

Who publishes on it

Institutions on the most papers of this approach since 2023 (of 40 papers; from OpenAlex and the papers' affiliations).

• International Digital Economy Academy · 4 papers
• Tsinghua University · 3 papers
• Nat’l Eng. Research Center of Visual Technology · 3 papers
• Peking University · 3 papers
• University of Central Florida · 2 papers
• Meta · 2 papers
• Konkuk University · 2 papers
• Electronics and Telecommunications Research Institute · 2 papers
• SenseTime · 2 papers
• Nanyang Technological University · 2 papers

Use it

Download BibTeX of 37 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

• Physics and sensor-based motion capture (125 papers)
• Human shape and pose regression (80 papers)
• Human motion prediction (38 papers)

Elsewhere in the topic

• Learned camera pose estimation (96 papers)
• Category-level object pose estimation (92 papers)
• Monocular 2D-to-3D pose lifting (90 papers)
• Depth-based hand pose regression (84 papers)
• Transformer-based multi-view 3D pose (83 papers)
• Temporal video pose estimation (76 papers)
• Instance-level 6D object pose (74 papers)
• Category-level pose estimation (54 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).