{"id":"https://openalex.org/W7155060649","doi":"https://doi.org/10.48550/arxiv.2604.16858","title":"Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement","display_name":"Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement","publication_year":2026,"publication_date":"2026-04-18","ids":{"openalex":"https://openalex.org/W7155060649","doi":"https://doi.org/10.48550/arxiv.2604.16858"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134104927","display_name":"Xudong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Xudong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124144029","display_name":"Jiaxi Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Jiaxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134124617","display_name":"Ziyin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Ziyin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134169536","display_name":"Yan Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134136775","display_name":"Zihao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002444427","display_name":"Jingyuan Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Jingyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134118565","display_name":"Yan Zhang","orcid":"https://orcid.org/0009-0001-8003-4547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054226277","display_name":"Xiawu Zheng","orcid":"https://orcid.org/0000-0002-6855-5403"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xiawu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134168079","display_name":"Rongrong Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Rongrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6467999815940857,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.6467999815940857,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.16680000722408295,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.03590000048279762,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6445000171661377},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6118000149726868},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5918999910354614},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5877000093460083},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.5467000007629395},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5454999804496765},{"id":"https://openalex.org/keywords/closing","display_name":"Closing (real estate)","score":0.4659999907016754},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4577000141143799}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312999963760376},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6445000171661377},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989000201225281},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5918999910354614},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5467000007629395},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5177000164985657},{"id":"https://openalex.org/C2778775528","wikidata":"https://www.wikidata.org/wiki/Q5135432","display_name":"Closing (real estate)","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4577000141143799},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4311000108718872},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35280001163482666},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C3020001037","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assessment","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Image":[0],"Quality":[1],"Assessment":[2],"(IQA)":[3],"models":[4,14],"are":[5],"increasingly":[6],"deployed":[7],"as":[8],"perceptual":[9],"critics":[10],"to":[11,79,104,113],"guide":[12,148],"generative":[13],"and":[15,45,85,108,130,158],"image":[16,150],"restoration.":[17],"This":[18],"role":[19],"demands":[20],"not":[21],"only":[22],"accurate":[23],"scores":[24],"but":[25],"also":[26],"actionable,":[27],"localized":[28],"feedback.":[29],"However,":[30],"current":[31],"MLLM-based":[32],"methods":[33],"adopt":[34],"a":[35,59,142],"single-look,":[36],"language-only":[37],"paradigm,":[38],"which":[39],"departs":[40],"from":[41],"human":[42],"evidence-seeking":[43],"judgment":[44],"yields":[46],"weakly":[47],"grounded":[48],"rationales,":[49],"limiting":[50],"their":[51],"reliability":[52],"for":[53,117],"in-the-loop":[54],"refinement.":[55,159],"We":[56],"propose":[57],"Q-DeepSight,":[58],"think-with-image":[60],"framework":[61,144],"that":[62],"emulates":[63],"this":[64],"human-like":[65],"process.":[66],"It":[67],"performs":[68],"interleaved":[69],"Multimodal":[70],"Chain-of-Thought":[71],"(iMCoT)":[72],"with":[73,139],"tool-augmented":[74],"evidence":[75],"acquisition":[76],"(e.g.,":[77],"crop-and-zoom)":[78],"explicitly":[80],"determine":[81],"where":[82,145],"quality":[83],"degrades":[84],"why.":[86],"To":[87],"train":[88],"these":[89],"long":[90],"iMCoT":[91],"trajectories":[92],"via":[93],"reinforcement":[94],"learning,":[95],"we":[96,134],"introduce":[97],"two":[98],"techniques:":[99],"Perceptual":[100],"Curriculum":[101],"Reward":[102],"(PCR)":[103],"mitigate":[105],"reward":[106],"sparsity":[107],"Evidence":[109],"Gradient":[110],"Filtering":[111],"(EGF)":[112],"improve":[114],"credit":[115],"assignment":[116],"visually-grounded":[118],"reasoning.":[119],"Q-DeepSight":[120],"achieves":[121],"state-of-the-art":[122],"performance":[123],"across":[124],"diverse":[125],"benchmarks,":[126],"including":[127],"natural,":[128],"restored,":[129],"AI-generated":[131],"content.":[132],"Furthermore,":[133],"demonstrate":[135],"its":[136],"practical":[137],"value":[138],"Perceptual-in-Generation":[140],"(PiG),":[141],"training-free":[143],"Q-DeepSight's":[146],"diagnoses":[147],"iterative":[149],"enhancement,":[151],"effectively":[152],"closing":[153],"the":[154],"loop":[155],"between":[156],"assessment":[157]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}