AI Paper Atlas

Research map / 3D vision / Human pose estimation

AIFit: Automatic 3D Human-Interpretable Feedback Models for Fitness Training

Mihai Fieraru, Mihai Zanfir, Silviu Cristian Pirlea, Vlad Olaru, Cristian Sminchisescu

CVPR 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 101 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
Fine-tune MubyNet on Fit3DMubyNet 3D pose reconstruction · Fit3D testMPJPE (mm), w/o Procrustes, SV: 90.4 -> 52.4Improved
Use multi-view instead of single-view reconstructionMubyNet · Fit3D testMPJPE (mm), w/o Procrustes: 90.4 -> 71.9; 52.4 -> 45.4Improved
Fine-tune MubyNet on Fit3DMubyNet 3D pose reconstruction · Fit3D testMPJPE (mm), w. Procrustes, SV: 67.7 -> 41.1Improved
Use multi-view instead of single-view reconstructionMubyNet · Fit3D testMPJPE (mm), w. Procrustes: 67.7 -> 57.9; 41.1 -> 35.7Improved
Use ground-truth 3D joints rather than estimated posesAIFit repetition segmentation · Fit3D testRepetition segmentation accuracy (IoU): 0.730 -> 0.731Improved
Use fine-tuned multi-view pose estimates instead of single-view MubyNet estimatesAIFit repetition segmentation · Fit3D testRepetition segmentation accuracy (IoU): 0.661 -> 0.730Improved
Use 3D pose representation rather than 2D pose representation (ablation)AIFit repetition counting · Fit3DOBO error: 0.920 -> 0.140Improved
Use AIFit repetition counting instead of RepNetRepetition counting · Fit3D testOBO error: 0.520 -> 0.140Improved
Use AIFit repetition counting instead of RepNetRepetition counting · Fit3D testMAE: 0.740 -> 0.253Improved
Use AIFit repetition counting instead of RepNetRepetition counting · CountixFitness validationOBO error: 0.292 -> 0.292No clear effect
Use AIFit repetition counting instead of RepNetRepetition counting · CountixFitness validationMAE: 0.468 -> 0.604Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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