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 221–230 of 517 papers

TitleStatusHype
High-Frequency Stereo Matching Network—0
Deep Eyes: Binocular Depth-from-Focus on Focal Stack Pairs—0
HeightFormer: A Multilevel Interaction and Image-adaptive Classification-regression Network for Monocular Height Estimation with Aerial Images—0
CV-HAZOP: Introducing Test Data Validation for Computer Vision—0
iELAS: An ELAS-Based Energy-Efficient Accelerator for Real-Time Stereo Matching on FPGA Platform—0
Gromov-Wasserstein Problem with Cyclic Symmetry—0
Cross-Modality 3D Object Detection—0
Graph Cut based Continuous Stereo Matching using Locally Shared Labels—0
Co-Teaching: An Ark to Unsupervised Stereo Matching—0
A Nearest Neighbor Network to Extract Digital Terrain Models from 3D Point Clouds—0
Show:102550
← PrevPage 23 of 52Next →

No leaderboard results yet.