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 101–125 of 517 papers

TitleStatusHype
Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume ExcitationCode1
Cost Volume Pyramid Network with Multi-strategies Range Searching for Multi-view StereoCode1
Active-Passive SimStereo -- Benchmarking the Cross-Generalization Capabilities of Deep Learning-based Stereo MethodsCode1
Stereo Matching by Training a Convolutional Neural Network to Compare Image PatchesCode1
3D Surface Reconstruction From Multi-Date Satellite ImagesCode1
Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene CompletionCode1
Discrete Time Convolution for Fast Event-Based StereoCode1
On the confidence of stereo matching in a deep-learning era: a quantitative evaluationCode1
Active Perception with A Monocular Camera for Multiscopic VisionCode1
Deep Laparoscopic Stereo Matching with TransformersCode1
A Flexible Framework for Designing Trainable Priors with Adaptive Smoothing and Game EncodingCode1
Learning Signed Distance Field for Multi-view Surface ReconstructionCode1
AANet: Adaptive Aggregation Network for Efficient Stereo MatchingCode1
Learning Stereo from Single ImagesCode1
Neural Rays for Occlusion-aware Image-based RenderingCode1
MVPSNet: Fast Generalizable Multi-view Photometric StereoCode1
LiDAR-Event Stereo Fusion with HallucinationsCode1
LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D DetectorCode1
Adaptive confidence thresholding for monocular depth estimationCode1
Depth-aware Volume Attention for Texture-less Stereo MatchingCode1
OmniStereo: Real-time Omnidireactional Depth Estimation with Multiview Fisheye CamerasCode1
MC-Stereo: Multi-peak Lookup and Cascade Search Range for Stereo MatchingCode1
Parallax Attention for Unsupervised Stereo Correspondence LearningCode1
Adaptive Multi-Modal Cross-Entropy Loss for Stereo MatchingCode1
When Epipolar Constraint Meets Non-local Operators in Multi-View StereoCode1
Show:102550
← PrevPage 5 of 21Next →

No leaderboard results yet.