Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation
Under stereo settings, the problem of image super-resolution (SR) and disparity estimation are interrelated that the result of each problem could help to solve the other. The effective exploitation of correspondence between different views facilitates the SR performance, while the high-resolution (HR) features with richer details benefit the correspondence estimation. According to this motivation, we propose a Stereo Super-Resolution and Disparity Estimation Feedback Network (SSRDE-FNet), which simultaneously handles the stereo image super-resolution and disparity estimation in a unified framework and interact them with each other to further improve their performance. Specifically, the SSRDE-FNet is composed of two dual recursive sub-networks for left and right views. Besides the cross-view information exploitation in the low-resolution (LR) space, HR representations produced by the SR process are utilized to perform HR disparity estimation with higher accuracy, through which the HR features can be aggregated to generate a finer SR result. Afterward, the proposed HR Disparity Information Feedback (HRDIF) mechanism delivers information carried by HR disparity back to previous layers to further refine the SR image reconstruction. Extensive experiments demonstrate the effectiveness and advancement of SSRDE-FNet.
Code (1)
Tasks
Disparity EstimationImage ReconstructionImage Super-ResolutionStereo Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Perception-Oriented Stereo Image Super-Resolution
Recent studies of deep learning based stereo image super-resolution (StereoSR) have promoted the development of StereoSR. However, existing StereoSR models mainly concentrate on improving quantitative evaluation metrics …
Disparity EstimationImage Super-ResolutionStereo Image Super-ResolutionSuper-ResolutionPseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matching
Self-supervised stereo matching holds great promise for application and research due to its independence from expensive labeled data. However, direct self-supervised stereo matching paradigms based on photometric loss fu…
Stereo MatchingBidNet: Binocular Image Dehazing Without Explicit Disparity Estimation
Heavy haze results in severe image degradation and thus hampers the performance of visual perception, object detection, etc. On the assumption that dehazed binocular images are superior to the hazy ones for stereo vision…
3D Object DetectionDisparity EstimationImage Dehazingobject-detection+1RFNet: Unsupervised Network for Mutually Reinforcing Multi-Modal Image Registration and Fusion
In this paper, we propose a novel method to realize multi-modal image registration and fusion in a mutually reinforcing framework, termed as RFNet. We handle the registration in a coarse-to-fine fashion. For the firs…
Image RegistrationMulti-Scale Boosted Dehazing Network with Dense Feature Fusion
In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we sho…
DecoderImage Dehazing