{"id":"https://openalex.org/W7155048813","doi":"https://doi.org/10.48550/arxiv.2604.16747","title":"Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting","display_name":"Incoherent Deformation, Not Capacity: Diagnosing and Mitigating Overfitting in Dynamic Gaussian Splatting","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155048813","doi":"https://doi.org/10.48550/arxiv.2604.16747"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16747","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","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.2604.16747","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058223043","display_name":"Ahmad Droby","orcid":"https://orcid.org/0000-0001-8458-1022"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Droby, Ahmad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5058223043"],"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/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.1517000049352646,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.1517000049352646,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10638","display_name":"Optical measurement and interference techniques","score":0.09139999747276306,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.07029999792575836,"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/gaussian","display_name":"Gaussian","score":0.566100001335144},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.4805999994277954},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.4438000023365021},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4433000087738037},{"id":"https://openalex.org/keywords/gaussian-random-field","display_name":"Gaussian random field","score":0.44200000166893005},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.38109999895095825},{"id":"https://openalex.org/keywords/gaussian-network-model","display_name":"Gaussian network model","score":0.3686999976634979},{"id":"https://openalex.org/keywords/additive-white-gaussian-noise","display_name":"Additive white Gaussian noise","score":0.35530000925064087},{"id":"https://openalex.org/keywords/deformation","display_name":"Deformation (meteorology)","score":0.34459999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6888999938964844},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.4438000023365021},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4433000087738037},{"id":"https://openalex.org/C51267290","wikidata":"https://www.wikidata.org/wiki/Q5527848","display_name":"Gaussian random field","level":4,"score":0.44200000166893005},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43939998745918274},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.38109999895095825},{"id":"https://openalex.org/C166550679","wikidata":"https://www.wikidata.org/wiki/Q263400","display_name":"Gaussian network model","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3626999855041504},{"id":"https://openalex.org/C169334058","wikidata":"https://www.wikidata.org/wiki/Q353292","display_name":"Additive white Gaussian noise","level":3,"score":0.35530000925064087},{"id":"https://openalex.org/C204366326","wikidata":"https://www.wikidata.org/wiki/Q3027650","display_name":"Deformation (meteorology)","level":2,"score":0.34459999203681946},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C179458375","wikidata":"https://www.wikidata.org/wiki/Q1020763","display_name":"Bundle adjustment","level":3,"score":0.30079999566078186},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C7218915","wikidata":"https://www.wikidata.org/wiki/Q1054475","display_name":"Gaussian function","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.2759000062942505},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26170000433921814},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2590999901294708},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16747","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16747","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.715232789516449,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dynamic":[0],"3D":[1],"Gaussian":[2,185,195,214],"Splatting":[3],"methods":[4],"achieve":[5],"strong":[6],"training-view":[7],"PSNR":[8,24,260],"on":[9,15,33,139,165,180],"monocular":[10,252],"video":[11,253],"but":[12],"generalize":[13],"poorly:":[14],"the":[16,58,78,83,91,131,140,151,157,183,192,218,258,265],"D-NeRF":[17],"benchmark":[18],"we":[19,200],"measure":[20],"an":[21],"average":[22],"train-test":[23],"gap":[25,92,103,152,219,244,261],"of":[26,45,52,57,77,125],"6.18":[27,94],"dB,":[28],"rising":[29],"to":[30,87,96,236],"11":[31],"dB":[32,95],"individual":[34],"scenes.":[35],"We":[36,128,231],"report":[37],"two":[38,202],"findings":[39],"that":[40,46,70,130,233],"together":[41],"account":[42],"for":[43,74],"most":[44],"gap.":[47],"Finding":[48,121],"1":[49],"(the":[50,123],"role":[51,124],"splitting).":[53],"A":[54,136],"systematic":[55],"ablation":[56],"Adaptive":[59],"Density":[60],"Control":[61],"pipeline":[62],"(split,":[63],"clone,":[64],"prune,":[65],"frequency,":[66],"threshold,":[67,209],"schedule)":[68],"shows":[69],"splitting":[71],"is":[72,104,134,188,279],"responsible":[73],"over":[75],"80%":[76],"gap:":[79],"disabling":[80],"split":[81],"collapses":[82],"cloud":[84,158],"from":[85,93],"44K":[86],"3K":[88],"Gaussians":[89],"and":[90,210,224,249],"1.15":[97],"dB.":[98],"Across":[99],"all":[100,177],"threshold-varying":[101],"ablations,":[102],"log-linear":[105],"in":[106,276],"count":[107],"(r":[108],"=":[109],"0.995,":[110],"bootstrap":[111],"95%":[112],"CI":[113],"[0.99,":[114],"1.00]),":[115],"which":[116],"suggests":[117],"a":[118,206,212,225,238],"capacity-based":[119],"explanation.":[120],"2":[122],"deformation":[126,142,240],"coherence).":[127],"show":[129],"capacity":[132],"explanation":[133],"incomplete.":[135],"local-smoothness":[137],"penalty":[138],"per-Gaussian":[141,162],"field":[143],"--":[144,149],"Elastic":[145],"Energy":[146],"Regularization":[147],"(EER)":[148],"reduces":[150,169,217],"by":[153,159,172,220,262,281],"40.8%":[154],"while":[155],"growing":[156],"85%.":[160],"Measuring":[161],"strain":[163,171],"directly":[164],"trained":[166],"checkpoints,":[167],"EER":[168,187],"mean":[170,259],"99.72%":[173],"(median":[174],"99.80%)":[175],"across":[176],"8":[178],"scenes;":[179],"8/8":[181],"scenes":[182],"median":[184],"under":[186,196],"less":[189],"strained":[190],"than":[191],"1st-percentile":[193],"(best-behaved)":[194],"baseline.":[197],"Alongside":[198],"EER,":[199],"evaluate":[201],"further":[203],"regularizers:":[204],"GAD,":[205],"loss-rate-aware":[207],"densification":[208],"PTDrop,":[211],"jitter-weighted":[213],"dropout.":[215],"GAD+EER":[216],"48%;":[221],"adding":[222],"PTDrop":[223],"soft":[226],"growth":[227],"cap":[228],"reaches":[229],"57%.":[230],"confirm":[232],"coherence":[234],"generalizes":[235],"(a)":[237],"different":[239],"architecture":[241],"(Deformable-3DGS,":[242],"+40.6%":[243],"reduction":[245],"at":[246,264],"re-tuned":[247],"lambda),":[248],"(b)":[250],"real":[251],"(4":[254],"HyperNeRF":[255],"scenes,":[256],"reducing":[257],"14.9%":[263],"same":[266],"lambda":[267],"as":[268],"D-NeRF,":[269],"with":[270],"near-zero":[271],"quality":[272],"cost).":[273],"The":[274],"overfitting":[275],"dynamic":[277],"3DGS":[278],"driven":[280],"incoherent":[282],"deformation,":[283],"not":[284],"parameter":[285],"count.":[286]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-22T00:00:00"}