AI Paper Atlas

Research map / 3D vision / Depth and stereo

Robust Homography Estimation via Dual Principal Component Pursuit

Tianjiao Ding, Yunchen Yang, Zhihui Zhu, Daniel P. Robinson, Rene Vidal, Laurent Kneip, Manolis C. Tsakiris

CVPR 2020 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 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 DPCP(1) with homographic embeddings instead of USAC with local optimizationRobust homography estimation · MS-COCO warped images, meantime: 16.6 -> 1.13Improved
Use DPCP(1) with homographic embeddings instead of USAC with local optimizationRobust homography estimation · MS-COCO warped images, meancorner error: 1.18 -> 2.53Hurt
Use epipolar embeddings and recover the homography from a 3-dimensional nullspace instead of homographic embeddings (ablation)DPCP homography estimation · MS-COCO warped images, meancorner error: 2.53 -> 5.08Hurt
Use epipolar embeddings and recover the homography from a 3-dimensional nullspace instead of homographic embeddings (ablation)DPCP homography estimation · MS-COCO warped images, mediancorner error: 0.81 -> 0.96Hurt
Disable progressive sampling in USAC while retaining local optimization (ablation)USAC homography estimation · MS-COCO warped images, meancorner error: 6.75 -> 1.18Improved
Use DPCP(1) instead of USAC with local optimizationTwo-view homography estimation · KITTI-8time: 13.1 -> 0.64Improved
Use DPCP(1) instead of USAC with local optimizationTwo-view homography estimation · KITTI-8rotation error: 0.42 -> 0.52Hurt
Estimate jointly from three views using DPCP(1) instead of using two-view DPCP(1) (ablation)DPCP homography estimation · KITTI-8rotation error: 0.52 -> 0.35Improved
Use DPCP(1) instead of USAC with local optimizationTwo-view homography estimation · TUM-neartime: 30.6 -> 0.84Improved
Use DPCP(1) instead of USAC with local optimizationTwo-view homography estimation · TUM-nearrotation error: 0.42 -> 0.46Hurt
Use DPCP(6) with trifocal embeddings instead of DPCP(1) with homographic embeddings (ablation)Three-view homography estimation · TUM-hemisphererotation error: 2.46 -> 1.32Hurt
Use DPCP(6) with trifocal embeddings instead of DPCP(1) with homographic embeddings (ablation)Three-view homography estimation · TUM-hemispheretime: 4.12 -> 2.70Improved

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