{"id":"https://openalex.org/W4416748155","doi":"https://doi.org/10.1109/iros60139.2025.11246657","title":"Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors","display_name":"Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748155","doi":"https://doi.org/10.1109/iros60139.2025.11246657"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5043199595","display_name":"Hritam Basak","orcid":"https://orcid.org/0000-0001-5921-1230"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hritam Basak","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082489194","display_name":"Hamid Tabatabaee","orcid":"https://orcid.org/0000-0002-2165-4666"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hadi Tabatabaee","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053446578","display_name":"Shreekant Gayaka","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreekant Gayaka","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705872","display_name":"Mingfeng Li","orcid":"https://orcid.org/0000-0002-8318-5754"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming-Feng Li","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100635997","display_name":"Xin Yang","orcid":"https://orcid.org/0000-0003-0445-6497"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Yang","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105792706","display_name":"Cheng-Hao Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Hao Kuo","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050826088","display_name":"Arnie Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnie Sen","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102008600","display_name":"Min Sun","orcid":"https://orcid.org/0000-0001-9598-8178"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["Amazon Lab126"],"affiliations":[{"raw_affiliation_string":"Amazon Lab126","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080054465","display_name":"Zhaozheng Yin","orcid":"https://orcid.org/0000-0002-9602-6488"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaozheng Yin","raw_affiliation_strings":["Stony Brook University"],"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5043199595"],"corresponding_institution_ids":["https://openalex.org/I1311688040"],"apc_list":null,"apc_paid":null,"fwci":1.307,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85944543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9987","last_page":"9994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7882000207901001,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.7882000207901001,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.062300000339746475,"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":0.03139999881386757,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.646399974822998},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4999000132083893},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4043999910354614},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4011000096797943},{"id":"https://openalex.org/keywords/3d-reconstruction","display_name":"3D reconstruction","score":0.3693000078201294},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.358599990606308},{"id":"https://openalex.org/keywords/texture-mapping","display_name":"Texture mapping","score":0.358599990606308},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33869999647140503},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.3345000147819519}],"concepts":[{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7817000150680542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.777400016784668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282999753952026},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.646399974822998},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.3693000078201294},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C200585589","wikidata":"https://www.wikidata.org/wiki/Q752176","display_name":"Texture mapping","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2777897806","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3D modeling","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C63099799","wikidata":"https://www.wikidata.org/wiki/Q17147001","display_name":"Image texture","level":4,"score":0.2734000086784363},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246657","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246657","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":45,"referenced_works":["https://openalex.org/W2096070062","https://openalex.org/W2963188159","https://openalex.org/W2963892972","https://openalex.org/W3025800305","https://openalex.org/W3130138602","https://openalex.org/W3141954417","https://openalex.org/W4200150166","https://openalex.org/W4221143294","https://openalex.org/W4281557677","https://openalex.org/W4285102264","https://openalex.org/W4312933868","https://openalex.org/W4360884927","https://openalex.org/W4383109335","https://openalex.org/W4385318467","https://openalex.org/W4386065887","https://openalex.org/W4386066287","https://openalex.org/W4386075660","https://openalex.org/W4386075859","https://openalex.org/W4386076286","https://openalex.org/W4386076476","https://openalex.org/W4386113267","https://openalex.org/W4389252802","https://openalex.org/W4390871705","https://openalex.org/W4390871887","https://openalex.org/W4390873120","https://openalex.org/W4390873331","https://openalex.org/W4390874424","https://openalex.org/W4390889720","https://openalex.org/W4391547698","https://openalex.org/W4399563687","https://openalex.org/W4401414745","https://openalex.org/W4401416702","https://openalex.org/W4402660131","https://openalex.org/W4402727236","https://openalex.org/W4402727917","https://openalex.org/W4402733585","https://openalex.org/W4402753761","https://openalex.org/W4402754209","https://openalex.org/W4402916825","https://openalex.org/W4402951568","https://openalex.org/W4402951629","https://openalex.org/W4403842396","https://openalex.org/W4403844572","https://openalex.org/W4403941285","https://openalex.org/W4405787569"],"related_works":[],"abstract_inverted_index":{"3D":[0,49,66,95,117],"object":[1,137],"generation":[2],"from":[3,93],"a":[4,53,81,94,104],"single":[5],"unposed":[6],"RGB":[7],"image":[8],"is":[9,20,30,143],"essential":[10,21],"for":[11,22,32,100,110,134,145],"robotic":[12,122,147],"perception,":[13],"as":[14],"reconstructing":[15],"complete":[16],"geometry":[17],"and":[18,26,35,103,140,150],"texture":[19],"precise":[23,146],"manipulation,":[24,149],"grasping,":[25,148],"scene":[27,151],"understanding,":[28],"which":[29,142],"key":[31],"autonomous":[33],"navigation":[34],"dexterous":[36],"interaction.":[37],"Recent":[38],"advancements":[39],"in":[40,158],"image-to-3D":[41],"employ":[42],"Gaussian":[43,88],"Splatting":[44],"with":[45,87],"pre-trained":[46],"2D":[47,56,105],"or":[48],"diffusion":[50,96,106],"models,":[51],"but":[52,71],"disparity":[54],"exists:":[55],"models":[57,67],"generate":[58],"high-fidelity":[59],"textures":[60],"yet":[61],"lack":[62],"geometric":[63,91],"consistency,":[64],"while":[65],"ensure":[68],"structural":[69,101],"coherence":[70],"produce":[72],"overly":[73],"smooth":[74],"textures.":[75,112],"To":[76],"address":[77],"this,":[78],"we":[79,126],"introduce":[80],"two-stage":[82],"frequency-based":[83],"distillation":[84],"loss":[85],"integrated":[86],"Splatting,":[89],"leveraging":[90],"priors":[92],"model\u2019s":[97,107],"low-frequency":[98],"spectrum":[99],"consistency":[102],"high-frequency":[108],"details":[109],"sharper":[111],"Our":[113],"approach":[114],"achieves":[115],"state-of-the-art":[116],"reconstruction":[118],"quality,":[119],"significantly":[120],"improving":[121],"perception":[123],"pipelines.":[124],"Additionally,":[125],"demonstrate":[127],"the":[128,159],"easy":[129],"adaptability":[130],"of":[131],"our":[132],"method":[133],"highly":[135],"accurate":[136],"pose":[138],"estimation":[139],"tracking,":[141],"critical":[144],"understanding.":[152],"Additional":[153],"results":[154],"can":[155],"be":[156],"found":[157],"supplementary":[160],"file.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-15T09:29:46.208133","created_date":"2025-11-28T00:00:00"}