AI Paper Atlas

Research map / 3D vision / Depth and stereo

SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation

Koutilya PNVR, Hao Zhou, David Jacobs

CVPR 2020 · 3D vision › Depth and stereo · approach: Foundation models for monocular geometry · 23 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
Map synthetic and real inputs into a task-relevant shared domain with SharinGANmonocular depth estimation · KITTI eigen test split, 50m capAbs Rel: 0.143 -> 0.109Improved
Map synthetic and real inputs into a task-relevant shared domain with SharinGANmonocular depth estimation · Make3D test setAbs Rel: 0.403 -> 0.377Improved
Add SharinGAN shared-domain mappingface normal estimation · Photoface test splitnormal accuracy < 20°: 43.6% -> 47.88}$\%Improved
Add SharinGAN shared-domain mappingface normal estimation · Photoface test splitMAE: 25.5$^{\circ}$ -> 24.0$^{\circ}$Improved
Add SharinGAN shared-domain mappingface geometry and lighting estimation · MultiPIEtop-1 accuracy: 80.25 -> 81.83Improved
Add SharinGAN mapping to synthetic and real training images (ablation)monocular depth estimation · KITTI eigen test split, 50m capAbs Rel: 0.137 -> 0.109Improved
Add reconstruction loss (ablation)SharinGAN monocular depth estimator · KITTI eigen test split, 50m capAbs Rel: 0.1113 -> 0.109Improved
Add SharinGAN mapping to synthetic and real training images (ablation)monocular depth estimation · Make3D test setAbs Rel: 0.476 -> 0.377Improved
Add reconstruction loss (ablation)SharinGAN monocular depth estimator · Make3D test setAbs Rel: 0.401 -> 0.377Improved

Later papers that compared with this method

1 later accepted paper reports SharinGAN as a baseline in their results tables; 1 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