AI Paper Atlas

Research map / 3D vision / Depth and stereo

EAR-Net: Pursuing End-to-End Absolute Rotations From Multi-View Images

Yuzhen Liu, Qiulei Dong

TPAMI 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 0 citations (OpenAlex)

Read the paperCheck 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
add end-to-end training with learned edge weights (ablation)EAR-Net · ScanNetMean rotation error (deg): 9.08 -> 4.03Improved
add end-to-end training (ablation)EAR-Net · ScanNetMedian rotation error (deg): 3.92 -> 2.06Improved
add pretraining of feature encoder and rotation branch (ablation)EAR-Net · ScanNetMean rotation error (deg): 6.05 -> 4.03Improved
add learned confidence branch (ablation)EAR-Net · ScanNetMean rotation error (deg): 9.31 -> 4.03Improved
add learned confidence branch (ablation)EAR-Net · ScanNetAcc@10deg: 78.71 -> 94.18Improved
add confidence-aware initialization (CAI) (ablation)EAR-Net · ScanNetMean rotation error (deg): 4.83 -> 4.03Improved
replace l2 loss with Cauchy loss (ablation)EAR-Net · ScanNetMean rotation error (deg): 9.31 -> 7.18Improved
replace l2 loss with Geman-McClure loss (ablation)EAR-Net · ScanNetMean rotation error (deg): 9.31 -> 7.36Improved
use proposed confidence-aware loss instead of Cauchy loss (ablation)EAR-Net · ScanNetMean rotation error (deg): 7.18 -> 4.03Improved
use designed confidence estimation instead of existing confidence regression objective (ablation)EAR-Net · ScanNetMean rotation error (deg): 7.07 -> 4.03Improved
train Reg6D and RAGO jointly end-to-end instead of two-stage (ablation)Reg6D+RAGO · ScanNetMean rotation error (deg): 11.87 -> 11.57Improved
train ExtremeRotation and RAGO jointly end-to-end instead of two-stage (ablation)ExtremeRotation+RAGO · ScanNetMean rotation error (deg): 9.83 -> 9.04Improved

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