{"id":"https://openalex.org/W4402980302","doi":"https://doi.org/10.1109/icme57554.2024.10687811","title":"Enhancing Zero-shot 3D Photography via Mesh-represented Image Inpainting","display_name":"Enhancing Zero-shot 3D Photography via Mesh-represented Image Inpainting","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980302","doi":"https://doi.org/10.1109/icme57554.2024.10687811"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10687811","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088688674","display_name":"Yuejian Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuejian Fang","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115594463","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0003-3926-3505"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Peking University,School of Software and Microelectronics,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Peking University,School of Software and Microelectronics,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088688674"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16524155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9986000061035156,"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":0.9986000061035156,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9969000220298767,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/inpainting","display_name":"Inpainting","score":0.9062782526016235},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.742119550704956},{"id":"https://openalex.org/keywords/photography","display_name":"Photography","score":0.6524205207824707},{"id":"https://openalex.org/keywords/computational-photography","display_name":"Computational photography","score":0.6131265759468079},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6103053689002991},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5617891550064087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5527474284172058},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5481796264648438},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5437702536582947},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5398769378662109},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.21763402223587036},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.16864946484565735},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.11971572041511536},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.1128920316696167}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9062782526016235},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.742119550704956},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.6524205207824707},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.6131265759468079},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6103053689002991},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5617891550064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5527474284172058},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5481796264648438},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5437702536582947},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5398769378662109},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.21763402223587036},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.16864946484565735},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.11971572041511536},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.1128920316696167},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10687811","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icme57554.2024.10687811","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2361248577","https://openalex.org/W3010334531","https://openalex.org/W2804670141","https://openalex.org/W2994735104","https://openalex.org/W2027349390","https://openalex.org/W1983639621","https://openalex.org/W2188751381","https://openalex.org/W1988828630","https://openalex.org/W1997064583","https://openalex.org/W2802215956"],"abstract_inverted_index":{"3D":[0,6,23,89,101,110],"photography":[1,90],"techniques":[2],"create":[3],"a":[4,9,69,100],"consistent":[5],"video":[7,102],"given":[8],"single":[10],"image.":[11],"Existing":[12],"methods":[13,33,55],"use":[14],"multi-plane":[15],"images":[16,20],"or":[17,72,167],"layered":[18],"depth":[19,125],"to":[21,68,94,108],"represent":[22,109],"scenes":[24,111],"and":[25,46,115,127],"then":[26],"render":[27],"subsequent":[28],"novel":[29],"views.":[30],"However,":[31],"these":[32,54,82],"involve":[34],"warping":[35],"pixels":[36],"across":[37],"frames,":[38],"which":[39,75],"easily":[40],"causes":[41],"distortions,":[42],"harms":[43],"visual":[44],"coherence,":[45],"lacks":[47],"controllable":[48],"generation":[49],"with":[50],"textual":[51],"prompts.":[52],"Moreover,":[53],"require":[56],"training":[57],"models":[58],"on":[59,148,159],"adequately":[60],"large":[61],"datasets":[62],"beforehand,":[63],"whether":[64],"they":[65],"are":[66],"tailored":[67],"specific":[70],"domain":[71],"open":[73],"domain,":[74],"requires":[76],"high":[77],"computational":[78],"resources.":[79],"To":[80,132],"address":[81],"issues,":[83],"we":[84,136],"propose":[85],"an":[86],"enhanced":[87],"zero-shot":[88],"method,":[91],"termed":[92],"Zero-3DP,":[93],"enable":[95],"rendering":[96],"any":[97],"image":[98],"into":[99],"anytime.":[103],"We":[104],"first":[105],"integrate":[106],"meshes":[107,117],"in":[112,130,162],"our":[113],"pipeline":[114],"update":[116],"along":[118],"predefined":[119],"trajectories,":[120],"ensuring":[121],"geometry":[122],"consistency":[123],"via":[124],"alignment":[126],"prior":[128],"preservation":[129],"rendering.":[131],"maintain":[133],"semantic":[134],"consistency,":[135],"test-time":[137,160],"fine-tune":[138],"the":[139,169],"diffusion-based":[140],"inpainting":[141],"module":[142],"for":[143],"each":[144],"incoming":[145],"frame.":[146],"Experiments":[147],"two":[149],"public":[150],"benchmarks":[151],"show":[152],"that":[153],"without":[154],"previous":[155],"training,":[156],"just":[157],"relying":[158],"fine-tuning":[161],"inference,":[163],"Zero-3DP":[164],"can":[165],"match":[166],"beat":[168],"state-of-the-art":[170],"methods.":[171]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}