{"id":"https://openalex.org/W7164833835","doi":"https://doi.org/10.1145/3805622.3810569","title":"HM-NVS: Hierarchical Multi-Modal Novel View Synthesis\\\\with Uncertainty-Aware Progressive Refinement","display_name":"HM-NVS: Hierarchical Multi-Modal Novel View Synthesis\\\\with Uncertainty-Aware Progressive Refinement","publication_year":2026,"publication_date":"2026-06-15","ids":{"openalex":"https://openalex.org/W7164833835","doi":"https://doi.org/10.1145/3805622.3810569"},"language":null,"primary_location":{"id":"doi:10.1145/3805622.3810569","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810569","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3805622.3810569","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134194332","display_name":"Jiahao Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Chang","raw_affiliation_strings":["Shanghai Jiaotong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-8884-5700","affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925038","display_name":"Haohua Zhao","orcid":"https://orcid.org/0000-0002-2414-4362"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohua Zhao","raw_affiliation_strings":["Shanghai Jiaotong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2414-4362","affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741568","display_name":"Liqing Zhang","orcid":"https://orcid.org/0000-0001-7597-8503"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqing Zhang","raw_affiliation_strings":["Shanghai Jiaotong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-7597-8503","affiliations":[{"raw_affiliation_string":"Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93699283,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1213","last_page":"1221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.3407999873161316,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.3407999873161316,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.21080000698566437,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1023000031709671,"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/granularity","display_name":"Granularity","score":0.6236000061035156},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5781000256538391},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4867999851703644},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48429998755455017},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/view-synthesis","display_name":"View synthesis","score":0.3797999918460846},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3686999976634979},{"id":"https://openalex.org/keywords/texture-synthesis","display_name":"Texture synthesis","score":0.3547999858856201},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7875000238418579},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6236000061035156},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5781000256538391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.53329998254776},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4551999866962433},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40070000290870667},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C50494287","wikidata":"https://www.wikidata.org/wiki/Q658467","display_name":"Texture synthesis","level":5,"score":0.3547999858856201},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.32120001316070557},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.30090001225471497},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2989087649","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Image synthesis","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.2551000118255615},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3805622.3810569","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810569","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3805622.3810569","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3805622.3810569","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.464530348777771,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2074254947","https://openalex.org/W2133665775","https://openalex.org/W2194775991","https://openalex.org/W2887976372","https://openalex.org/W2962677625","https://openalex.org/W2962785568","https://openalex.org/W2962793285","https://openalex.org/W2963850211","https://openalex.org/W3176368002","https://openalex.org/W3204647170","https://openalex.org/W3215769467","https://openalex.org/W4200150166","https://openalex.org/W4214520160","https://openalex.org/W4285102264","https://openalex.org/W4312933868","https://openalex.org/W4312956471","https://openalex.org/W4385318467","https://openalex.org/W4386065887","https://openalex.org/W4386075660","https://openalex.org/W4386075859","https://openalex.org/W4386113267","https://openalex.org/W4390873331","https://openalex.org/W4390874575","https://openalex.org/W4399563697","https://openalex.org/W4402733576","https://openalex.org/W4402733585"],"related_works":[],"abstract_inverted_index":{"Novel":[0,54],"view":[1],"synthesis":[2],"(NVS)":[3],"from":[4,27],"a":[5,28,58,69,88],"single":[6],"image":[7],"is":[8],"fundamental":[9],"for":[10],"multimedia":[11],"applications":[12],"including":[13],"virtual/augmented":[14],"reality":[15],"and":[16,42,73,81,97,103,121,130,143],"interactive":[17],"3D":[18,90],"content":[19],"retrieval.":[20],"Despite":[21],"notable":[22],"progress,":[23],"diffusion-based":[24],"methods":[25],"suffer":[26],"persistent":[29],"semantic":[30,71,98],"gap:":[31],"global":[32],"textual":[33],"conditioning":[34],"lacks":[35],"the":[36],"granularity":[37],"to":[38,114,141],"preserve":[39],"part-level":[40],"attributes":[41],"inter-part":[43],"spatial":[44],"relationships":[45],"under":[46],"large":[47],"viewpoint":[48],"changes.":[49],"We":[50],"present":[51],"Hierarchical":[52],"Multi-Modal":[53],"View":[55],"Synthesis":[56],"(HM-NVS),":[57],"framework":[59],"that":[60,77,93,110,124],"bridges":[61],"this":[62],"gap":[63],"through":[64],"three":[65],"synergistic":[66],"contributions:":[67],"(1)":[68],"hierarchical":[70],"extraction":[72],"adaptive":[74],"fusion":[75],"mechanism":[76],"integrates":[78],"global,":[79],"part-level,":[80],"geometric":[82,96],"cues":[83],"with":[84,138],"view-dependent":[85],"weighting;":[86],"(2)":[87],"semantic-augmented":[89],"attention":[91],"module":[92],"jointly":[94],"enforces":[95],"consistency":[99],"across":[100],"generated":[101],"views;":[102],"(3)":[104],"an":[105],"uncertainty-aware":[106],"progressive":[107],"refinement":[108],"strategy":[109],"selectively":[111],"allocates":[112],"computation":[113],"difficult":[115],"regions.":[116],"Experiments":[117],"on":[118],"GSO,":[119],"RTMV,":[120],"OmniObject3D":[122],"demonstrate":[123],"HM-NVS":[125],"improves":[126],"PSNR":[127],"by":[128,133],"15%":[129],"reduces":[131],"LPIPS":[132],"20%":[134],"over":[135],"state-of-the-art":[136],"methods,":[137],"robust":[139],"generalisation":[140],"non-rigid":[142],"articulated":[144],"objects.":[145]},"counts_by_year":[],"updated_date":"2026-06-16T07:37:23.134862","created_date":"2026-06-16T00:00:00"}