computer-vision-1
Stereo Matching
3260 papers • 126 benchmarks • 313 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
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in stereo-matching-1
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find stereo-matching-1 models and implementations
3 papers 660
Datasets
Subtasks
No subtasks available.
Most implemented papers
HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
Yinda Zhang, S. Fanello, S. Izadi, V. Tankovich, Christian Häne, Sofien Bouaziz•Wed Jul 22 2020
HITNet is a novel neural network architecture for real-time stereo matching that not only geometrically reasons about disparities but also infers slanted plane hypotheses allowing to more accurately perform geometric warping and upsampling operations.
278