{"id":{"repo_id":"umkc","oai_identifier":"oai:mospace.umsystem.edu:10355/70898"},"canonical_url":"https://search.dev.ndltd.org/etd/umkc/oai:mospace.umsystem.edu:10355/70898","repository":{"repo_id":"umkc","name":"University of Missouri - Kansas City","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"Improving Extreme Low-light Image Denoising via Residual Learning","abstract":"Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work with the noise under extremely low light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computation cost which makes them impractical to use in real-time applications or where the computational resource is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the performance over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state of the art methods.","abstract_html":"Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work with the noise under extremely low light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computation cost which makes them impractical to use in real-time applications or where the computational resource is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the performance over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state of the art methods.","abstract_has_math":false,"creators":["Maharjan, Paras"],"institution":"University of Missouri--Kansas City","degree_name":"M.S. (Master of Science)","degree_level":"Masters","degree_discipline":"Electrical Engineering (UMKC)","degree_department":null,"school":null,"contributors":[],"advisors":["Li, Zhu"],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-07-24T05:18:34Z","subjects":[],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10355/70898","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Li, Zhu"]},{"key":"dc:creator","label":"Author","values":["Maharjan, Paras"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-01-02T23:01:13Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-01-02T23:01:13Z"]},{"key":"dc:date.issued","label":"Date","values":["2019"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering (UMKC)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. (Master of Science)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Kansas City"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/70898"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Title from PDF of title page viewed January 7, 2020","Thesis advisor: Zhu Li","Vita","Includes bibliographical references (page 21-23)","Thesis (M.S.)--School of Computing and Engineering. University of Missouri--Kansas City, 2019"]},{"key":"dc:description.abstract","label":"Abstract","values":["Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work with the noise under extremely low light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computation cost which makes them impractical to use in real-time applications or where the computational resource is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the performance over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state of the art methods."]},{"key":"dc:title","label":"Title","values":["Improving Extreme Low-light Image Denoising via Residual Learning"]}]}],"canonical_facts":{"dc:contributor.advisor":["Li, Zhu"],"dc:creator":["Maharjan, Paras"],"dc:date.accessioned":["2020-01-02T23:01:13Z"],"dc:date.available":["2020-01-02T23:01:13Z"],"dc:date.issued":["2019"],"dc:description":["Title from PDF of title page viewed January 7, 2020","Thesis advisor: Zhu Li","Vita","Includes bibliographical references (page 21-23)","Thesis (M.S.)--School of Computing and Engineering. University of Missouri--Kansas City, 2019"],"dc:description.abstract":["Taking a satisfactory picture in a low-light environment remains a challenging problem. Low-light imaging mainly suffers from noise due to the low signal-to-noise ratio. Many methods have been proposed for the task of image denoising, but they fail to work with the noise under extremely low light conditions. Recently, deep learning based approaches have been presented that have higher objective quality than traditional methods, but they usually have high computation cost which makes them impractical to use in real-time applications or where the computational resource is limited. In this paper, we propose a new residual learning based deep neural network for end-to-end extreme low-light image denoising that can not only significantly reduce the computational cost but also improve the performance over existing methods in both objective and subjective metrics. Specifically, in one setting we achieved 29x speedup with higher PSNR. Subjectively, our method provides better color reproduction and preserves more detailed texture information compared to state of the art methods."],"dc:identifier.uri":["https://hdl.handle.net/10355/70898"],"dc:title":["Improving Extreme Low-light Image Denoising via Residual Learning"],"thesis:degree_discipline":["Electrical Engineering (UMKC)"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S. (Master of Science)"],"thesis:institution_name":["University of Missouri--Kansas City"]},"updated_at":"2026-07-24T05:18:34Z"}