AI Paper Atlas

Research map / 3D vision / Depth and stereo

SceneSqueezer: Learning To Compress Scene for Camera Relocalization

Luwei Yang, Rakesh Shrestha, Wenbo Li, Shuaicheng Liu, Guofeng Zhang, Zhaopeng Cui, Ping Tan

CVPR 2022 · 3D vision › Depth and stereo · approach: Scene coordinate regression for localization · 33 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 SceneSqueezer instead of QP+RootSIFT scene compressionCambridge Landmarks localization · Cambridge Landmarks: Shop Facademedian translation error (m): 0.72 -> 0.11Improved
Use SceneSqueezer instead of QP+RootSIFT scene compressionCambridge Landmarks localization · Cambridge Landmarks: Old Hospitalmedian translation error (m): 0.9 -> 0.37Improved
Use SceneSqueezer instead of QP+RootSIFT scene compressionCambridge Landmarks localization · Cambridge Landmarks: King’s Collegemedian translation error (m): 1.53 -> 0.27Improved
Use SceneSqueezer instead of QP+RootSIFT scene compressionCambridge Landmarks localization · Cambridge Landmarks: St. Mary’s Churchmedian translation error (m): 0.56 -> 0.15Improved
Use SceneSqueezer instead of HLocAachen Day-Night localization · Aachen Day-Night: Aachen Daylocalization recall @ 0.5m, 5° (%): 95.4 -> 89.7Hurt
Use SceneSqueezer instead of HLocAachen Day-Night localization · Aachen Day-Night: Aachen Nightlocalization recall @ 0.5m, 5° (%): 93.9 -> 67.3Hurt
Use SceneSqueezer instead of HLocAachen Day-Night localization · Aachen Day-Nightscene size (MB): 7828 -> 31Improved
Use SceneSqueezer instead of Cascaded descriptor compressionAachen Day-Night localization · Aachen Day-Night: Aachen Nightlocalization recall @ 0.5m, 5° (%): 48.0 -> 67.3Improved
Fuse verification-frame features using appearance and geometric similarity (ablation)Differentiable Point Selection · Cambridge Landmarkspercentage of selected points with under 10px reprojection errorImproved
Add a learned feature-based term to the spatial proximity kernel (ablation)Differentiable Point Selection · King’s Collegelocalization recall @ 0.5m, 5°Improved
Use spatial proximity with learned distinctiveness instead of selecting only top distinctiveness scores (ablation)Differentiable Point Selection · King’s Collegelocalization recall @ 0.5m, 5°Improved
Use learned point selection instead of random point selection (ablation)Differentiable Point Selection · King’s Collegelocalization recall @ 0.5m, 5°Improved

Later papers that compared with this method

1 later accepted paper reports SceneSqueezer as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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