Simultaneous deep stereo matching and dehazing with feature attention

DOI10.1007/S11263-020-01294-2MaRDI QIDQ2193554zbMATH OpenOpenAlexWikidataFDO

Authors Taeyong Song, Youngjung Kim, Changjae Oh, Hyunsung Jang, Namkoo Ha, Kwanghoon Sohn

Publication date 20 August 2020

Published in International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL https://qmro.qmul.ac.uk/xmlui/handle/123456789/62679

zbMATH Keywords

multi-task learningstereo matchingCNNknowledge distillationadverse weather conditiondehazingstereo confidence

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Machine vision and scene understanding (68T45)

Recommendations

• Stereo matching by training a convolutional neural network to compare image patches
• Single image dehazing based on multiple convolutional neural networks
• Single image dehazing and denoising: a fast variational approach
• Multiscale single image dehazing based on adaptive wavelet fusion
• Integration of optical flow and multi-path-Viterbi algorithm for stereo vision

Cites work

• A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior
• A taxonomy and evaluation of dense two-frame stereo correspondence algorithms
• Accurate Stereo Matching by Two-Step Energy Minimization
• DehazeNet: An End-to-End System for Single Image Haze Removal
• Multiple View Geometry in Computer Vision
• Stereo matching by training a convolutional neural network to compare image patches

Cited in

(1)

• Stereo matching by training a convolutional neural network to compare image patches

Describes a project that uses

Uses Software

• TensorFlow
• Adam
• KITTI
• FlowNet
• MatchNet
• Cityscapes
• DehazeNet
• AOD-Net

This page was built for publication: Simultaneous deep stereo matching and dehazing with feature attention

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2193554)