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 1–25 of 517 papers

TitleStatusHype
S^2M^2: Scalable Stereo Matching Model for Reliable Depth Estimation—0
Learning Robust Stereo Matching in the Wild with Selective Mixture-of-ExpertsCode2
RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather—0
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo MatchingCode2
StereoDiff: Stereo-Diffusion Synergy for Video Depth Estimation—0
Multi-Label Stereo Matching for Transparent Scene Depth EstimationCode1
Diving into the Fusion of Monocular Priors for Generalized Stereo MatchingCode1
M3Depth: Wavelet-Enhanced Depth Estimation on Mars via Mutual Boosting of Dual-Modal Data—0
Boosting Zero-shot Stereo Matching using Large-scale Mixed Images Sources in the Real World—0
CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo MatchingCode0
ThermoStereoRT: Thermal Stereo Matching in Real Time via Knowledge Distillation and Attention-based RefinementCode0
Consistency-aware Self-Training for Iterative-based Stereo Matching—0
Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation ModelCode1
Distilling Stereo Networks for Performant and Efficient Leaner NetworksCode0
LeanStereo: A Leaner Backbone based Stereo NetworkCode0
GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised MatchingCode2
RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization—0
Stereo Any Video: Temporally Consistent Stereo Matching—0
BANet: Bilateral Aggregation Network for Mobile Stereo MatchingCode2
LightEndoStereo: A Real-time Lightweight Stereo Matching Method for Endoscopy ImagesCode1
SurgPose: a Dataset for Articulated Robotic Surgical Tool Pose Estimation and Tracking—0
FoundationStereo: Zero-Shot Stereo MatchingCode7
DEFOM-Stereo: Depth Foundation Model Based Stereo MatchingCode3
StereoGen: High-quality Stereo Image Generation from a Single Image—0
MonSter: Marry Monodepth to Stereo Unleashes PowerCode4
Show:102550
← PrevPage 1 of 21Next →

No leaderboard results yet.