{"id":{"repo_id":"texas","oai_identifier":"oai:repositories.lib.utexas.edu:2152/78636"},"canonical_url":"https://search.dev.ndltd.org/etd/texas/oai:repositories.lib.utexas.edu:2152/78636","repository":{"repo_id":"texas","name":"University of Texas","base_url":"https://repositories.lib.utexas.edu/server/oai/request"},"display":{"title":"Artistic and semantic progressive image coding","abstract":"Progressive image coding provides web users a faster full-image preview when only a small fraction of the file has been transmitted. JPEG is the most widely used progressive compression technique. However, the compressed quality is low at low bitrates and it entirely ignores the semantics of images. We propose to render different artistic visual effects and leverage semantic information in the images. The key insight is human visual system is more sensitive to luminance and semantic salient objects. Our learning based progressive coding approach learns to encode a smooth transition from grayscale images to color images. During decoding, our approach will display sharp grayscale images first instead of blurry color images, which allows viewers to preview images faster. In addition, our approach can allocate more bitrates to important objects according to segmentation masks. The approach can be extended to encode other artistic styles such as mosaic style and users can easily create their own decoding patterns. Our progressive image coding method generates clearer content than JPEG and previous learning based progressive compression method in both quantitative metrics and user studies.","abstract_html":"Progressive image coding provides web users a faster full-image preview when only a small fraction of the file has been transmitted. JPEG is the most widely used progressive compression technique. However, the compressed quality is low at low bitrates and it entirely ignores the semantics of images. We propose to render different artistic visual effects and leverage semantic information in the images. The key insight is human visual system is more sensitive to luminance and semantic salient objects. Our learning based progressive coding approach learns to encode a smooth transition from grayscale images to color images. During decoding, our approach will display sharp grayscale images first instead of blurry color images, which allows viewers to preview images faster. In addition, our approach can allocate more bitrates to important objects according to segmentation masks. The approach can be extended to encode other artistic styles such as mosaic style and users can easily create their own decoding patterns. Our progressive image coding method generates clearer content than JPEG and previous learning based progressive compression method in both quantitative metrics and user studies.","abstract_has_math":false,"creators":["Cheng, Chia-Wen"],"institution":"The University of Texas at Austin","degree_name":"Master of Science in Computer Sciences","degree_level":"Masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Krähenbühl, Philipp"],"committee_chairs":[],"committee_members":["Grauman, Kristen"],"year":2019,"date_issued":"2019-06-26","date_published":"2019-06-26","updated_at":"2026-07-24T05:01:10Z","subjects":["Image compression","Progressive image coding","Deep image compression","Bit allocation"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://dx.doi.org/10.26153/tsw/5692"],"render_values":[{"text":"http://dx.doi.org/10.26153/tsw/5692","href":"http://dx.doi.org/10.26153/tsw/5692","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/2152/78636","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Krähenbühl, Philipp"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Grauman, Kristen"]},{"key":"dc:creator","label":"Author","values":["Cheng, Chia-Wen"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2019-12-04T16:36:50Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2019-12-04T16:36:50Z"]},{"key":"dc:date.issued","label":"Date","values":["2019-06-26"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Sciences"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["The University of Texas at Austin"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Image compression","Progressive image coding","Deep image compression","Bit allocation"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/2152/78636","http://dx.doi.org/10.26153/tsw/5692"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Progressive image coding provides web users a faster full-image preview when only a small fraction of the file has been transmitted. JPEG is the most widely used progressive compression technique. However, the compressed quality is low at low bitrates and it entirely ignores the semantics of images. We propose to render different artistic visual effects and leverage semantic information in the images. The key insight is human visual system is more sensitive to luminance and semantic salient objects. Our learning based progressive coding approach learns to encode a smooth transition from grayscale images to color images. During decoding, our approach will display sharp grayscale images first instead of blurry color images, which allows viewers to preview images faster. In addition, our approach can allocate more bitrates to important objects according to segmentation masks. The approach can be extended to encode other artistic styles such as mosaic style and users can easily create their own decoding patterns. Our progressive image coding method generates clearer content than JPEG and previous learning based progressive compression method in both quantitative metrics and user studies."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Artistic and semantic progressive image coding"]}]}],"canonical_facts":{"dc:contributor.advisor":["Krähenbühl, Philipp"],"dc:contributor.committeemember":["Grauman, Kristen"],"dc:creator":["Cheng, Chia-Wen"],"dc:date.accessioned":["2019-12-04T16:36:50Z"],"dc:date.available":["2019-12-04T16:36:50Z"],"dc:date.issued":["2019-06-26"],"dc:description.abstract":["Progressive image coding provides web users a faster full-image preview when only a small fraction of the file has been transmitted. JPEG is the most widely used progressive compression technique. However, the compressed quality is low at low bitrates and it entirely ignores the semantics of images. We propose to render different artistic visual effects and leverage semantic information in the images. The key insight is human visual system is more sensitive to luminance and semantic salient objects. Our learning based progressive coding approach learns to encode a smooth transition from grayscale images to color images. During decoding, our approach will display sharp grayscale images first instead of blurry color images, which allows viewers to preview images faster. In addition, our approach can allocate more bitrates to important objects according to segmentation masks. The approach can be extended to encode other artistic styles such as mosaic style and users can easily create their own decoding patterns. Our progressive image coding method generates clearer content than JPEG and previous learning based progressive compression method in both quantitative metrics and user studies."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/2152/78636","http://dx.doi.org/10.26153/tsw/5692"],"dc:language.iso":["en"],"dc:subject":["Image compression","Progressive image coding","Deep image compression","Bit allocation"],"dc:title":["Artistic and semantic progressive image coding"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science in Computer Sciences"],"thesis:institution_name":["The University of Texas at Austin"]},"updated_at":"2026-07-24T05:01:10Z"}