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 326–350 of 517 papers

TitleStatusHype
Du^2Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels—0
Superpixel Segmentation with Fully Convolutional NetworksCode1
FADNet: A Fast and Accurate Network for Disparity EstimationCode1
Scene Completeness-Aware Lidar Depth Completion for Driving ScenarioCode1
Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning—0
A Robust Real-Time Computing-based Environment Sensing System for Intelligent Vehicle—0
Active Perception with A Monocular Camera for Multiscopic VisionCode1
Depth-Based Selective Blurring in Stereo Images Using Accelerated FrameworkCode0
A hybrid algorithm for disparity calculation from sparse disparity estimates based on stereo visionCode0
Correcting Decalibration of Stereo Cameras in Self-Driving Vehicles—0
A shallow feature extraction network with a large receptive field for stereo matching tasks—0
Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost VolumeCode0
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo MatchingCode1
Hierarchical Deep Stereo Matching on High-resolution ImagesCode0
Sub-pixel matching method for low-resolution thermal stereo images—0
Domain-invariant Stereo Matching NetworksCode0
A Comparative Evaluation of SGM Variants (including a New Variant, tMGM) for Dense Stereo Matching—0
Shift Convolution Network for Stereo Matching—0
ASV: Accelerated Stereo Vision SystemCode0
Learning Dense Wide Baseline Stereo Matching for People—0
Semantic Stereo Matching With Pyramid Cost Volumes—0
Real-Time Semantic Stereo Matching—0
Real-Time Variational Fisheye Stereo without Rectification and UndistortionCode0
Object-Centric Stereo Matching for 3D Object Detection—0
Learning Residual Flow as Dynamic Motion from Stereo Videos—0
Show:102550
← PrevPage 14 of 21Next →

No leaderboard results yet.