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 26–50 of 517 papers

TitleStatusHype
Selective-Stereo: Adaptive Frequency Information Selection for Stereo MatchingCode2
RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo MatchingCode2
Attention Concatenation Volume for Accurate and Efficient Stereo MatchingCode2
MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular BackbonesCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
Accurate and Efficient Stereo Matching via Attention Concatenation VolumeCode2
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical FlowCode2
Neural Markov Random Field for Stereo MatchingCode2
GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised MatchingCode2
DCVSMNet: Double Cost Volume Stereo Matching NetworkCode1
Adaptive confidence thresholding for monocular depth estimationCode1
Deep 3D Portrait from a Single ImageCode1
ActiveStereoNet: End-to-End Self-Supervised Learning for Active Stereo SystemsCode1
AANet: Adaptive Aggregation Network for Efficient Stereo MatchingCode1
Deep Laparoscopic Stereo Matching with TransformersCode1
Active Perception with A Monocular Camera for Multiscopic VisionCode1
Active-Passive SimStereo -- Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo MethodsCode1
3D Surface Reconstruction From Multi-Date Satellite ImagesCode1
GA-Net: Guided Aggregation Net for End-to-end Stereo MatchingCode1
Flow2Stereo: Effective Self-Supervised Learning of Optical Flow and Stereo MatchingCode1
Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view StereoCode1
Global Occlusion-Aware Transformer for Robust Stereo MatchingCode1
ChiTransformer:Towards Reliable Stereo from CuesCode1
Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume ExcitationCode1
Epipolar TransformersCode1
Show:102550
← PrevPage 2 of 21Next →

No leaderboard results yet.