Stereo Matching
150 papers with code • 0 benchmarks • 18 datasets
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
Benchmarks
These leaderboards are used to track progress in Stereo Matching
Libraries
Use these libraries to find Stereo Matching models and implementationsDatasets
Latest papers
MoCha-Stereo: Motif Channel Attention Network for Stereo Matching
In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation.
Robust Confidence Intervals in Stereo Matching using Possibility Theory
To the best of our knowledge, this is the first method creating disparity confidence intervals based on the cost volume.
RoadBEV: Road Surface Reconstruction in Bird's Eye View
This paper uniformly proposes two simple yet effective models for road elevation reconstruction in BEV named RoadBEV-mono and RoadBEV-stereo, which estimate road elevation with monocular and stereo images, respectively.
Neural Markov Random Field for Stereo Matching
Stereo matching is a core task for many computer vision and robotics applications.
Robust Synthetic-to-Real Transfer for Stereo Matching
With advancements in domain generalized stereo matching networks, models pre-trained on synthetic data demonstrate strong robustness to unseen domains.
Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching
Stereo matching methods based on iterative optimization, like RAFT-Stereo and IGEV-Stereo, have evolved into a cornerstone in the field of stereo matching.
Digging Into Normal Incorporated Stereo Matching
To enhance geometric consistency, especially in low-texture regions, the estimated normal map is then leveraged to calculate a local affinity matrix, providing the residual learning with information about where the correction should refer and thus improving the residual learning efficiency.
DCVSMNet: Double Cost Volume Stereo Matching Network
We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost volumes.
Depth-aware Volume Attention for Texture-less Stereo Matching
Furthermore, we propose a more rigorous evaluation metric that considers depth-wise relative error, providing comprehensive evaluations for universal stereo matching and depth estimation models.
Icy Moon Surface Simulation and Stereo Depth Estimation for Sampling Autonomy
The surface reflectance properties of icy moon terrains (Enceladus and Europa) are inferred from multispectral datasets of previous missions.