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 331–340 of 517 papers

TitleStatusHype
2T-UNET: A Two-Tower UNet with Depth Clues for Robust Stereo Depth Estimation—0
3D Hand Pose Tracking and Estimation Using Stereo Matching—0
3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model—0
3D Reconstruction of Curvilinear Structures with Stereo Matching DeepConvolutional Neural Networks—0
3D Scene Geometry Estimation from 360^ Imagery: A Survey—0
A Brief Survey of Recent Edge-Preserving Smoothing Algorithms on Digital Images—0
Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?—0
Accurate Human Body Reconstruction for Volumetric Video—0
Accurate Optical Flow via Direct Cost Volume Processing—0
Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning—0
Show:102550
← PrevPage 34 of 52Next →

No leaderboard results yet.