AI Paper Atlas

Research map / 3D vision / Human pose estimation

GFPose: Learning 3D Human Pose Prior With Gradient Fields

Hai Ci, Mingdong Wu, Wentao Zhu, Xiaoxuan Ma, Hao Dong, Fangwei Zhong, Yizhou Wang

CVPR 2023 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 70 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use the score-based generative pose estimator rather than the deterministic counterpart (ablation)Human3.6M pose estimation · Human3.6M Protocol #1, GT 2D train/testMPJPE (mm): 41.9 -> 35.6Improved
Increase hypotheses from S=10 to S=200GFPose · Human3.6M Protocol #1minMPJPE (mm): 45.1 -> 35.6Improved
Generate 200 pose hypotheses instead of using the strongest listed baselineHuman3.6M multi-hypothesis estimation · Human3.6M Protocol #1minMPJPE (mm): 44.3 -> 35.6Improved
Add part-level condition masking with p_p=0.1 (ablation)GFPose · Human3.6M Protocol #1, single hypothesisminMPJPE (mm): 51.0 -> 50.5Improved
Add joint-level condition masking with p_j=0.1 (ablation)GFPose · Human3.6M Protocol #1, single hypothesisminMPJPE (mm): 51.0 -> 51.7Hurt
Use mixed condition masking in unified U2D rather than no masking (ablation)GFPose · Human3.6M Protocol #1, 200 hypothesesminMPJPE (mm): 35.6 -> 36.7Hurt
Train with a unified U3D model that also conditions on 3D poses (ablation)GFPose · Human3.6M Protocol #1, 200 hypothesesminMPJPE (mm): 36.7 -> 35.9Mixed
Reduce sampling steps from 1k to 0.5k (ablation)GFPose · Human3.6M Protocol #1, 200 hypothesesminMPJPE (mm): 35.6 -> 36.1Hurt
Increase sampling steps from 1k to 2k (ablation)GFPose · Human3.6M Protocol #1, 200 hypothesesminMPJPE (mm): 35.6 -> 35.7No clear effect
Increase score-network depth from 2 to 3 residual blocks (ablation)GFPose · Human3.6M Protocol #1, 200 hypothesesminMPJPE (mm): 35.6 -> 37.2Hurt
Reduce hidden dimension from 1024 to 512 (ablation)GFPose · Human3.6M Protocol #1, 200 hypothesesminMPJPE (mm): 35.6 -> 44.3Hurt
Augment a small real-pose training set with 2,438 generated posesDeterministic pose estimator · Human3.6M Protocol #1, 2,438 real posesMPJPE (mm): 66.1 -> 60.0Improved

Later papers that compared with this method

1 later accepted paper reports GFPose as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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