SOTAVerified

Stereo Matching

Stereo Matching is one of the core technologies in computer vision, which recovers 3D structures of real world from 2D images. It has been widely used in areas such as autonomous driving, augmented reality and robotics navigation. Given a pair of rectified stereo images, the goal of Stereo Matching is to compute the disparity for each pixel in the reference image, where disparity is defined as the horizontal displacement between a pair of corresponding pixels in the left and right images.

Source: Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 271–280 of 517 papers

TitleStatusHype
Semi-synthesis: A fast way to produce effective datasets for stereo matching—0
KCP: Kernel Cluster Pruning for Dense Labeling Neural Networks—0
On the confidence of stereo matching in a deep-learning era: a quantitative evaluationCode1
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation—0
UASNet: Uncertainty Adaptive Sampling Network for Deep Stereo Matching—0
Adaptive Deconvolution-based stereo matching Net for Local Stereo Matching—0
Pseudo Label-Guided Multi Task Learning for Scene Understanding—0
Direct Depth Learning Network for Stereo Matching—0
Displacement-Invariant Cost Computation for Efficient Stereo Matching—0
ADCPNet: Adaptive Disparity Candidates Prediction Network for Efficient Real-Time Stereo Matching—0
Show:102550
← PrevPage 28 of 52Next →

No leaderboard results yet.