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 126–150 of 517 papers

TitleStatusHype
ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite ImagesCode1
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow EstimationCode1
Real-Time Variational Fisheye Stereo without Rectification and UndistortionCode0
Real-Time Dense Stereo Matching With ELAS on FPGA Accelerated Embedded DevicesCode0
Rethinking the Key Factors for the Generalization of Remote Sensing Stereo Matching NetworksCode0
Depth-Based Selective Blurring in Stereo Images Using Accelerated FrameworkCode0
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNsCode0
PWOC-3D: Deep Occlusion-Aware End-to-End Scene Flow EstimationCode0
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchCode0
OpenCL-based FPGA accelerator for disparity map generation with stereoscopic event camerasCode0
Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor ScenesCode0
An Inference Algorithm for Multi-Label MRF-MAP Problems with Clique Size 100Code0
Cross-Scale Cost Aggregation for Stereo MatchingCode0
Noise-Aware Unsupervised Deep Lidar-Stereo FusionCode0
Active Event-based Stereo VisionCode0
Continuous 3D Label Stereo Matching using Local Expansion MovesCode0
Continual Stereo Matching of Continuous Driving Scenes With Growing ArchitectureCode0
An Adversarial Generative Network Designed for High-Resolution Monocular Depth Estimation from 2D HiRISE Images of MarsCode0
OmniMVS: End-to-End Learning for Omnidirectional Stereo MatchingCode0
Computing the Stereo Matching Cost with a Convolutional Neural NetworkCode0
A Lightweight Target-Driven Network of Stereo Matching for Inland WaterwaysCode0
Color Agnostic Cross-Spectral Disparity EstimationCode0
Learning Monocular Depth by Distilling Cross-domain Stereo NetworksCode0
Learning monocular depth estimation infusing traditional stereo knowledgeCode0
CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo MatchingCode0
Show:102550
← PrevPage 6 of 21Next →

No leaderboard results yet.