AI Paper Atlas

Research map / 3D vision / Depth and stereo

Learning Transformation Synchronization

Xiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas J. Guibas, Qixing Huang

CVPR 2019 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 57 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 learned recurrent weighting and synchronization instead of FastGR pairwise alignments aloneFastGR alignments · Redwood testmean rotation error: 34.1^{\circ} -> 6.9^{\circ}Improved
Use learned recurrent weighting and synchronization instead of FastGR pairwise alignments aloneFastGR alignments · Redwood testmean translation error: 0.58m -> 0.26mImproved
Use learned recurrent weighting and synchronization instead of FastGR pairwise alignments aloneFastGR alignments · ScanNet testmean rotation error: 68.8^{\circ} -> 42.9^{\circ}Improved
Use learned recurrent weighting and synchronization instead of FastGR pairwise alignments aloneFastGR alignments · ScanNet testmean translation error: 1.43m -> 1.16mImproved
Replace RotAvg with learned recurrent weighting and synchronizationFastGR alignments · Redwood testmean rotation error: 22.4^{\circ} -> 6.9^{\circ}Improved
Replace RotAvg with learned recurrent weighting and synchronizationFastGR alignments · Redwood testmean translation error: 0.418m; reduction: 39.0\%Improved
Replace RotAvg with learned recurrent weighting and synchronizationFastGR alignments · ScanNet testmean rotation error: reduction: 33.3\%Improved
Replace RotAvg with learned recurrent weighting and synchronizationFastGR alignments · ScanNet testmean translation error: reduction: 7.4\%Improved
Jointly learn the weighting module rather than fixing its initial map weights (ablation)Learning Transformation Synchronization · Redwood testmean rotation error: 13.7^{\circ} -> 6.9^{\circ}Improved
Jointly learn the weighting module rather than fixing its initial map weights (ablation)Learning Transformation Synchronization · Redwood testmean translation error: 0.255m -> 0.26mImproved
Use recurrent weighting and synchronization rather than a single synchronization layer (ablation)Learning Transformation Synchronization · Redwood and ScanNetmean pose errorImproved

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