{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/lapran-a-scalable-laplacian-pyramid","title":"LAPRAN: A Scalable Laplacian Pyramid Reconstructive Adversarial Network for Flexible Compressive Sensing Reconstruction","arxiv_id":"1807.09388","date":"2018-07-24","proceeding":"ECCV 2018 9","authors":["Kai Xu","Zhikang Zhang","Fengbo Ren"],"abstract":"This paper addresses the single-image compressive sensing (CS) and\nreconstruction problem. We propose a scalable Laplacian pyramid reconstructive\nadversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS\nimages reconstruction. LAPRAN progressively reconstructs an image following the\nconcept of Laplacian pyramid through multiple stages of reconstructive\nadversarial networks (RANs). At each pyramid level, CS measurements are fused\nwith a contextual latent vector to generate a high-frequency image residual.\nConsequently, LAPRAN can produce hierarchies of reconstructed images and each\nwith an incremental resolution and improved quality. The scalable pyramid\nstructure of LAPRAN enables high-fidelity CS reconstruction with a flexible\nresolution that is adaptive to a wide range of compression ratios (CRs), which\nis infeasible with existing methods. Experimental results on multiple public\ndatasets show that LAPRAN offers an average 7.47dB and 5.98dB PSNR, and an\naverage 57.93% and 33.20% SSIM improvement compared to model-based and\ndata-driven baselines, respectively.","url_abs":"http://arxiv.org/abs/1807.09388v3","url_pdf":"http://arxiv.org/pdf/1807.09388v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"lapran-a-scalable-laplacian-pyramid","repo_url":"https://github.com/PSCLab-ASU/LAPRAN-PyTorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"compressive-sensing","task_name":"Compressive Sensing"},{"task_slug":"ssim","task_name":"SSIM"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1807.09388","atlas_url":"https://app.syntology.ai/?focus=1807.09388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}