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 1–50 of 517 papers

TitleStatusHype
FoundationStereo: Zero-Shot Stereo MatchingCode7
MonSter: Marry Monodepth to Stereo Unleashes PowerCode4
IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo MatchingCode4
A Survey on Deep Stereo Matching in the TwentiesCode4
DEFOM-Stereo: Depth Foundation Model Based Stereo MatchingCode3
Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono FailCode3
RoadBEV: Road Surface Reconstruction in Bird's Eye ViewCode3
GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo ViewsCode3
Unifying Flow, Stereo and Depth EstimationCode3
An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022Code3
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-ExpertsCode2
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo MatchingCode2
GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised MatchingCode2
BANet: Bilateral Aggregation Network for Mobile Stereo MatchingCode2
Motif Channel Opened in a White-Box: Stereo Matching via Motif Correlation GraphCode2
Event-based Stereo Depth Estimation: A SurveyCode2
Temporally Consistent Stereo MatchingCode2
MoCha-Stereo: Motif Channel Attention Network for Stereo MatchingCode2
Robust Confidence Intervals in Stereo Matching using Possibility TheoryCode2
Neural Markov Random Field for Stereo MatchingCode2
Robust Synthetic-to-Real Transfer for Stereo MatchingCode2
Selective-Stereo: Adaptive Frequency Information Selection for Stereo MatchingCode2
A Simple Framework for 3D Occupancy Estimation in Autonomous DrivingCode2
Iterative Geometry Encoding Volume for Stereo MatchingCode2
CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry InteractionCode2
GeoMVSNet: Learning Multi-View Stereo With Geometry PerceptionCode2
CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical FlowCode2
Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object DetectionCode2
Accurate and Efficient Stereo Matching via Attention Concatenation VolumeCode2
MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular BackbonesCode2
Practical Stereo Matching via Cascaded Recurrent Network with Adaptive CorrelationCode2
Attention Concatenation Volume for Accurate and Efficient Stereo MatchingCode2
QuadTree Attention for Vision TransformersCode2
RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo MatchingCode2
Multi-Label Stereo Matching for Transparent Scene Depth EstimationCode1
Diving into the Fusion of Monocular Priors for Generalized Stereo MatchingCode1
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ModelCode1
LightEndoStereo: A Real-time Lightweight Stereo Matching Method for Endoscopy ImagesCode1
Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching TransformerCode1
OmniStereo: Real-time Omnidireactional Depth Estimation with Multiview Fisheye CamerasCode1
Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-worldCode1
Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo MatchingCode1
Disparity Estimation Using a Quad-Pixel SensorCode1
LiDAR-Event Stereo Fusion with HallucinationsCode1
Temporal Event Stereo via Joint Learning with Stereoscopic FlowCode1
Stereo-LiDAR Depth Estimation with Deformable Propagation and Learned Disparity-Depth ConversionCode1
DCVSMNet: Double Cost Volume Stereo Matching NetworkCode1
Depth-aware Volume Attention for Texture-less Stereo MatchingCode1
S3Net: Innovating Stereo Matching and Semantic Segmentation with a Single-Branch Semantic Stereo Network in Satellite Epipolar ImageryCode1
BDIS-SLAM: A lightweight CPU-based dense stereo SLAM for surgeryCode1
Show:102550
← PrevPage 1 of 11Next →

No leaderboard results yet.