AI Paper Atlas

Research map / 3D vision / Human pose estimation

Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction

Yana Hasson, Bugra Tekin, Federica Bogo, Ivan Laptev, Marc Pollefeys, Cordelia Schmid

CVPR 2020 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 186 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 proposed direct 6D object-pose regression instead of the baseline approachhand-object reconstruction · FPHAB action splitobject error (mm): 24.9 -> 22.3Improved
use the proposed hand-pose model instead of the baseline approachhand-object reconstruction · FPHAB action splithand error (mm): 15.8 -> 18.0Hurt
add a skeleton adaptation layer (ablation)hand reconstruction · FPHABhand error (mm): 28.1 -> 27.4Improved
jointly train hand and object pose estimation rather than train each separately (ablation)hand-object reconstruction · FPHABhand error (mm): 15.7 -> 18.0Hurt
jointly train hand and object pose estimation rather than train each separately (ablation)hand-object reconstruction · FPHABobject error (mm): 21.8 -> 22.3Hurt
add photometric-consistency self-supervision to sparse-frame traininghand-object reconstruction · HO-3D, below 10% fully annotated framespose estimation accuracyImproved
add photometric-consistency self-supervision to training with less than one percent of the data fully supervisedhand-object reconstruction · FPHAB2D reprojection error: 7 pixels for objects and 4 pixels for hands; ... 25 and 23%Improved
add photometric-consistency self-supervision with 2.5% of data fully supervisedobject pose estimation · FPHAB3D object error (mm): 4.7 ... 51% ... 40%Improved
add photometric-consistency self-supervisionobject pose estimation · HO-3D3D object reconstruction scoreNo clear effect

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