Original Image * = Compressive Sensing using Single Pixel Camera (15% measurements) Ours PSNR: 29.68 dB TVAL3 PSNR: 24.70 dB Reconstructed Image D-AMP PSNR: 26.76 dBFigure 1: We propose to use a deep generative model, RIDE [27], as an image prior for compressive signal recovery. Since RIDE models long-range dependency in images using spatial LSTM, we are able to recover the image better than other competing methods.
AbstractReconstruction of signals from compressively sensed measurements is an ill-posed problem. In this paper, we leverage the recurrent generative model, RIDE, as an image prior for compressive image reconstruction. Recurrent networks can model long-range dependencies in images and hence are suitable to handle global multiplexing in reconstruction from compressive imaging. We perform MAP inference with RIDE using back-propagation to the inputs and projected gradient method. We propose an entropy thresholding based approach for preserving texture in images well. Our approach shows superior reconstructions compared to recent global reconstruction approaches like D-AMP and TVAL3 on both simulated and real data.
In this work, we introduce a new class of self-maps which satisfy the (E.A.) property with respect to some q ∈ M, where M is q-starshaped subset of a convex metric space and common fixed point results are established for this new class of self-maps. After that we obtain some invariant approximation results as an application. Our results represent a very strong variant of the several recent results existing in the literature. We also provide some illustrative examples in the support of proved results. MSC: 46T99; 47H10; 54H25
In this work, we introduce the class of α-ψ-Geraghty contraction as well as generalized α-ψ-Geraghty contraction mappings in the context of generalized metric spaces where ψ is an auxiliary function which does not require the subadditive property and set up some fixed point results for both classes individually. Our results will extend, improve and generalize several existing results in the literature. MSC: 46T99; 47H10; 54H25
We establish a fixed point theorem for Cirić contraction in the context of convex b-metric spaces. Furthermore, we ensure that there is a fixed point for the maps satisfying the condition (B) (a kind of almost contraction ) in convex b-metric spaces and demonstrate its uniqueness as well. Supporting examples to substantiate the generality of the proved results are given.
In this work, the concept of almost contraction for multi-valued mappings in the setting of cone metric spaces is defined and then we establish some fixed point and common fixed point results in the set-up of cone metric spaces. As an application, some invariant approximation results are obtained. The results of this paper extend and improve the corresponding results of multi-valued mapping from metric space theory to cone metric spaces. Further our results improve the recent result of Arshad and Ahmad (Sci. World J. 2013:481601, 2013.
MSC: 46T99; 47H10; 54H25
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.