AI Paper Atlas

Research map / 3D vision / Depth and stereo

Unsupervised Learning of Stereo Matching

Chao Zhou, Hong Zhang, Xiaoyong Shen, Jiaya Jia

ICCV 2017 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 167 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 the learned joint filtering cost aggregation branch (ablation)stereo network · KITTI 2015 supervised>3 pixel error: 9.23 -> 6.81Improved
add the learned joint filtering cost aggregation branch (ablation)stereo network · KITTI 2015 supervised>5 pixel error: 7.12 -> 5.01Improved
use learned joint filtering instead of box filter (ablation)stereo network · KITTI 2015 supervised>3 pixel error: 7.33 -> 6.81Improved
use learned joint filtering instead of guided filter (ablation)stereo network · KITTI 2015 supervised>3 pixel error: 7.13 -> 6.81Improved
use learned joint filtering instead of guided filter (ablation)stereo network · KITTI 2015 supervised>5 pixel error: 5.28 -> 5.01Improved
initialize with DeepMatching instead of random network (ablation)unsupervised stereo · KITTI 2015>3 pixel error: 7.81 -> 7.69No clear effect
initialize with DeepMatching instead of random network (ablation)unsupervised stereo · KITTI 2015>5 pixel error: 6.01 -> 5.67No clear effect
iterative confident-match unsupervised training instead of unsupervised optical-flow losses (USCNN)unsupervised stereo · KITTI 2015 NOC test>3 pixel error: 11.17 -> 8.61Improved
iterative confident-match unsupervised training instead of Yu et al.unsupervised stereo · KITTI 2015 All test>3 pixel error: 19.14 -> 9.91Improved
new network architecture instead of DispNet (supervised)stereo network · KITTI 2015 NOC>3 pixel error: 7.19 -> 6.81Improved
new network architecture instead of DispNet (supervised)stereo network · KITTI 2015runtime: 0.12 -> 0.39Hurt

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