AI Paper Atlas

Research map / 3D vision / Depth and stereo

End-To-End Learning of Geometry and Context for Deep Stereo Regression

Alex Kendall, Hayk Martirosyan, Saumitro Dasgupta, Peter Henry, Ryan Kennedy, Abraham Bachrach, Adam Bry

ICCV 2017 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 1,573 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 3-D convolutional regularization layers to unary features (ablation)GC-Net · Scene Flow testerror >1 px (%): 97.9 -> 16.9Improved
add 3-D convolutional regularization layers to unary features (ablation)GC-Net · Scene Flow testMAE (px): 36.6 -> 2.51Improved
add hierarchical encoder-decoder 3-D context instead of single scale (ablation)GC-Net · Scene Flow testerror >1 px (%): 34.6 -> 16.9Improved
add hierarchical 3-D context instead of single scale (ablation)GC-Net · Scene Flow testRMS (px): 20.4 -> 12.4Improved
use regression (soft argmin, L1) loss instead of hard classification loss (ablation)GC-Net · Scene Flow testerror >1 px (%): 19.2 -> 16.9Improved
use regression loss instead of hard classification loss (ablation)GC-Net · Scene Flow testMAE (px): 5.01 -> 2.51Improved
use regression loss instead of soft classification loss (ablation)GC-Net · Scene Flow testRMS (px): 25.1 -> 12.4Improved
use classification loss instead of regression loss for training speed (ablation)GC-Net · Scene Flow validationtraining convergenceMixed
use classification loss with unaries only instead of regression loss (ablation)Unaries only · Scene Flow testerror >1 px (%): 97.9 -> 51.9Improved
use end-to-end GC-Net instead of best prior methodGC-Net · KITTI 2015 testD1-all error (%): 3.43 -> 2.87Improved
use end-to-end GC-Net instead of Displets v2GC-Net · KITTI 2012 test (>3 px, all)error rate (%): 3.09 -> 2.30Improved
use GC-Net instead of DispNetC on foreground pixelsGC-Net · KITTI 2015 testD1-fg error (%): 4.41 -> 6.16Hurt

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