AI Paper Atlas

Research map / 3D vision / Depth and stereo

Geometric Loss Functions for Camera Pose Regression With Deep Learning

Alex Kendall, Roberto Cipolla

CVPR 2017 · 3D vision › Depth and stereo · approach: Dense feature matching for correspondence · 815 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
replace the fixed position-orientation weight with learned homoscedastic task uncertaintyPoseNet · Cambridge Landmarks, King's Collegeaccuracy <2m, 5°: 65.0% -> 85.3%Improved
replace the fixed position-orientation weight with learned homoscedastic task uncertaintyPoseNet · Dubrovnik 6Kaccuracy <10m, 10°: 30.1% -> 41.7%Improved
fine-tune a homoscedastic-uncertainty-pretrained model with reprojection lossPoseNet · Cambridge Landmarks, King's Collegeaccuracy <2m, 5°: 85.3% -> 90.3%Improved
fine-tune a homoscedastic-uncertainty-pretrained model with reprojection lossPoseNet · Dubrovnik 6Kaccuracy <10m, 10°: 41.7% -> 48.6%Improved
train with reprojection loss from random initialization rather than pretrained weights (ablation)PoseNet · Cambridge Landmarks, King's CollegeconvergenceHurt
use robust Huber or Tukey regression norms instead of L1 (ablation)PoseNet · datasets used in the paperlocalization performanceHurt
use reprojection loss instead of learned homoscedastic weighting (ablation)PoseNet · Cambridge Landmarks and 7 Scenesmedian position error: King's College: 0.99m -> 0.88m; Old Hospital: 2.17m -> 3.20m; Chess: 0.14m -> 0.13mMixed

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