AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning To Regress Bodies From Images Using Differentiable Semantic Rendering

Sai Kumar Dwivedi, Nikos Athanasiou, Muhammed Kocabas, Michael J. Black

ICCV 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 67 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
add DSR-C and DSR-MC losses (ablation)C-EFT regressor · 3DPWPA-MPJPE: 58.5 -> 57.2Improved
add DSR-C and DSR-MC losses (ablation)C-EFT regressor · 3DPWPVE: 119.3 -> 116.3Improved
add full-body silhouette per-pixel supervision (DSR-FB) (ablation)C-EFT · 3DPWPA-MPJPE: 58.5 -> 59.8Hurt
use soft-DistM loss for full-body silhouette (DSR-FB s-DistM) (ablation)C-EFT · 3DPWPA-MPJPE: 58.5 -> 58.0Improved
add clothing semantics (DSR-C + DSR-MC) over cloth-agnostic DSR-FB s-DistM (ablation)C-EFT · 3DPWPA-MPJPE: 58.0 -> 57.2Improved
use probabilistic semantic prior instead of manual vertex painting (MVP) (ablation)DSR · 3DPWPA-MPJPE: 58.1 -> 57.2Improved
add DSR-C alone (ablation)C-EFT · 3DPWPA-MPJPE: 58.5 -> 57.6Improved
add DSR-MC alone (s-IoU) (ablation)C-EFT · 3DPWPA-MPJPE: 58.5 -> 58.0Improved
use soft-IoU instead of soft-DistM for DSR-MC (ablation)DSR-MC · 3DPWPA-MPJPE: 58.2 -> 58.0Improved
add DSR loss to standard lossSD regressor · Human3.6M subsetPA-MPJPE: 47.5 -> 45.1Improved
add DSR loss to standard lossSD regressor · Human3.6M subsetPVE: 99.2 -> 96.6Improved
add DSR loss to standard loss, per jointSD regressor · Human3.6M subset ankle errorjoint error: 99.3 -> 96.1Improved

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