{"id":"https://openalex.org/W4405033576","doi":"https://doi.org/10.1145/3702250.3702292","title":"Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention","display_name":"Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention","publication_year":2024,"publication_date":"2024-12-13","ids":{"openalex":"https://openalex.org/W4405033576","doi":"https://doi.org/10.1145/3702250.3702292"},"language":"en","primary_location":{"id":"doi:10.1145/3702250.3702292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702250.3702292","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702250.3702292?download=true","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 Fifteenth Indian Conference on Computer Vision Graphics and Image Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3702250.3702292?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ajith Balakrishnan","orcid":"https://orcid.org/0009-0003-9910-970X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ajith Balakrishnan","raw_affiliation_strings":["College of Engineering, Trivandrum, Trivandrum, IN"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Trivandrum, Trivandrum, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101486737","display_name":"S. Sreeja","orcid":"https://orcid.org/0000-0002-8155-8377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sreeja S","raw_affiliation_strings":["College of Engineering Trivandrum, Trivandrum, IN"],"affiliations":[{"raw_affiliation_string":"College of Engineering Trivandrum, Trivandrum, IN","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090821716","display_name":"Linu Shine","orcid":"https://orcid.org/0000-0003-4526-6075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linu Shine","raw_affiliation_strings":["College of Engineering, Trivandrum, Trivandrum, IN"],"affiliations":[{"raw_affiliation_string":"College of Engineering, Trivandrum, Trivandrum, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3821,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89322091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9997000098228455,"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/T11211","display_name":"3D Surveying and Cultural Heritage","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8133082389831543},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7480602860450745},{"id":"https://openalex.org/keywords/rgb-color-model","display_name":"RGB color model","score":0.6564576029777527},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5969690084457397},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5686317086219788},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.5046132802963257},{"id":"https://openalex.org/keywords/solid-modeling","display_name":"Solid modeling","score":0.49643856287002563},{"id":"https://openalex.org/keywords/virtual-reality","display_name":"Virtual reality","score":0.4851685166358948},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.4670746624469757},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4102781116962433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36475348472595215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8133082389831543},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7480602860450745},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.6564576029777527},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5969690084457397},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5686317086219788},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.5046132802963257},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.49643856287002563},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.4851685166358948},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4670746624469757},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4102781116962433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36475348472595215},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3702250.3702292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702250.3702292","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702250.3702292?download=true","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 Fifteenth Indian Conference on Computer Vision Graphics and Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.00731","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.00731","pdf_url":"https://arxiv.org/pdf/2412.00731","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3702250.3702292","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702250.3702292","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702250.3702292?download=true","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 Fifteenth Indian Conference on Computer Vision Graphics and Image Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405033576.pdf","grobid_xml":"https://content.openalex.org/works/W4405033576.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1951742130","https://openalex.org/W1991264156","https://openalex.org/W2151103935","https://openalex.org/W2342277278","https://openalex.org/W2461937780","https://openalex.org/W2464708700","https://openalex.org/W2963002018","https://openalex.org/W2963221299","https://openalex.org/W2964153986","https://openalex.org/W2968370607","https://openalex.org/W3005938584","https://openalex.org/W3124420883","https://openalex.org/W4360858873"],"related_works":["https://openalex.org/W3027020613","https://openalex.org/W2016533837","https://openalex.org/W3167885074","https://openalex.org/W2892386716","https://openalex.org/W1998563493","https://openalex.org/W4306164210","https://openalex.org/W4313316311","https://openalex.org/W4362608745","https://openalex.org/W2135446119","https://openalex.org/W4285723685"],"abstract_inverted_index":{"Generating":[0],"3D":[1,45,77,84,114],"models":[2,127],"from":[3,59,86,92],"multi-view":[4,113],"2D":[5,90],"RGB":[6],"images":[7,91],"has":[8],"gained":[9],"significant":[10],"attention,":[11],"extending":[12],"the":[13,70,97,117],"capabilities":[14],"of":[15],"technologies":[16],"like":[17],"Virtual":[18],"Reality,":[19],"Robotic":[20],"Vision,":[21],"and":[22,34,43,79,112],"human-machine":[23],"interaction.In":[24],"this":[25],"paper,":[26],"we":[27],"introduce":[28],"a":[29,37,44,50],"hybrid":[30],"strategy":[31],"combining":[32],"CNNs":[33],"transformers,":[35],"featuring":[36],"visual":[38],"auto-encoder":[39],"with":[40,105],"self-attention":[41,71],"mechanisms":[42],"refiner":[46],"network,":[47],"trained":[48],"using":[49,96],"novel":[51],"Joint":[52],"Train":[53],"Separate":[54],"Optimization":[55],"(JTSO)":[56],"algorithm.Encoded":[57],"features":[58],"unordered":[60],"inputs":[61],"are":[62],"transformed":[63],"into":[64,74],"an":[65,75],"enhanced":[66],"feature":[67],"map":[68],"by":[69,128],"layer,":[72],"decoded":[73],"initial":[76],"volume,":[78],"further":[80],"refined.Our":[81],"network":[82],"generates":[83],"voxels":[85],"single":[87,111],"or":[88],"multiple":[89],"arbitrary":[93],"viewpoints.Performance":[94],"evaluations":[95],"ShapeNet":[98],"datasets":[99],"show":[100],"that":[101],"our":[102],"approach,":[103],"combined":[104],"JTSO,":[106],"outperforms":[107],"state-of-the-art":[108],"techniques":[109],"in":[110,130],"reconstruction,":[115],"achieving":[116],"highest":[118],"mean":[119],"intersection":[120],"over":[121],"union":[122],"(IOU)":[123],"scores,":[124],"surpassing":[125],"other":[126],"4.2%":[129],"single-view":[131],"reconstruction.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}