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 391–400 of 517 papers

TitleStatusHype
Wide baseline stereo matching with convex bounded-distortion constraints—0
Wide Baseline Stereo Matching With Convex Bounded Distortion Constraints—0
Widening siamese architectures for stereo matching—0
One-view occlusion detection for stereo matching with a fully connected CRF model—0
On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey—0
OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline—0
Open-World Stereo Video Matching with Deep RNN—0
ORStereo: Occlusion-Aware Recurrent Stereo Matching for 4K-Resolution Images—0
PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation—0
Parameterized Cost Volume for Stereo Matching—0
Show:102550
← PrevPage 40 of 52Next →

No leaderboard results yet.