AI Paper Atlas

Research map / 3D vision / Human pose estimation

Human Mesh Recovery From Multiple Shots

Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa

CVPR 2022 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 44 citations (OpenAlex)

Check 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 changedWhereMeasuredEffect
Add MS-AVA training data to HMRHMR single-frame model · Partial Humans Uncropped (VLOG)PCKh: 86.9 -> 90.3Improved
Add MS-AVA training data to HMRHMR single-frame model · Partial Humans Uncropped (YouCook)PCKh: 96.8 -> 98.9Improved
Add MS-AVA training data to HMRHMR single-frame model · Partial Humans Uncropped (Instr)PCKh: 92.4 -> 94.1Improved
Add MS-AVA training data to HMRHMR single-frame model · Partial Humans Uncropped (Cross)PCKh: 96.2 -> 98.2Improved
Add MS-AVA training data to HMRHMR single-frame model · 3DPWPA-MPJPE (mm): 59.2 -> 57.8Improved
Replace the recurrent temporal encoder with a transformerTemporal human mesh recovery · 3DPW testPA-MPJPE (mm): 56.5 -> 56.1Improved
Use a transformer instead of convolutional or recurrent temporal encodingTemporal human mesh recovery · AVA (train: clean, test: clean)cross-shot PCK: 68.8; 70.8; 70.7No clear effect
Train with sequences containing missing frames and use a transformer temporal encoderTemporal human mesh recovery · AVA (train: all, test: clean)cross-shot PCK: 68.8 -> 73.8Improved
Use a transformer temporal encoder on sequences with missing framesTemporal human mesh recovery · AVA (train: all, test: all)cross-shot PCK: 67.5; 68.5; 70.7Improved
Use a transformer temporal encoder rather than convolutional or recurrent encodingTemporal human mesh recovery · VIBE training settingtraining stabilityImproved
Use multi-shot optimization rather than single-frame or single-shot optimization3D human mesh reconstruction · AVA cross-shot evaluationcross-shot PCKImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy