AI Paper Atlas

Research map / 3D vision / Face and shape

PAUL: Procrustean Autoencoder for Unsupervised Lifting

Chaoyang Wang, Simon Lucey

CVPR 2021 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 15 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
Use the Procrustean auto-encoder prior instead of the compared NRSfM methodsPAUL · CMU motion capture S1, S5, S64, S70, S123normalized error: 10.74 -> 4.97; 13.40 -> 4.38; 4.38 -> 0.39; 2.17 -> 0.77; 2.23 -> 0.59Improved
Use the Procrustean auto-encoder prior instead of the strongest listed baselinePAUL · Pascal3D+ mean and 8 classesnormalized error (%): 10.3 -> 8.4; 7.58 -> 5.32Improved
Use PAUL instead of Deep NRSfM++PAUL · UP3D 79KP testMPJPE: 0.062 -> 0.058Improved
Use PAUL instead of PRNPAUL · SURREAL testnormalized error (%): 13.77 -> 12.36Improved
Use PAUL instead of PRNPAUL · H3.6M validationMPJPE: 86.4 -> 88.3; 124.5 -> 132.5Hurt
Add the auto-encoder reconstruction term to the decoder-only approach (ablation)PAUL · CMU motion capturereconstruction errorImproved
Add a low-rank constraint to the decoder-only approach (ablation)ADL + low rank · CMU motion capturereconstruction errorMixed
Vary bottleneck dimension from 2 to 12 (ablation)PAUL · NRSfM datasetsnormalized errorNo clear effect
Use a larger bottleneck dimension on noisy data (ablation)PAUL · CMU motion capture with Gaussian keypoint noisereconstruction accuracyHurt
Use the auto-encoder objective rather than decoder-only learning (ablation)PAUL versus ADL · Latent-space visualization on motion sequenceslatent trajectory continuityImproved

Later papers that compared with this method

4 later accepted papers report PAUL as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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