Diffusion Schrodinger bridge for unpaired day-to-night event translation슈뢰딩거 브리지 기반 확산 모델을 이용한 쌍을 이루지 않는 낮에서 밤으로의 이벤트 전환

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 3
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisor윤국진-
dc.contributor.authorJeong, Yuhwan-
dc.contributor.author정유환-
dc.date.accessioned2024-07-30T19:30:28Z-
dc.date.available2024-07-30T19:30:28Z-
dc.date.issued2024-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1095976&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/321308-
dc.description학위논문(석사) - 한국과학기술원 : 기계공학과, 2024.2,[vi, 50 p. :]-
dc.description.abstractEvent camera with a high dynamic range ensures scene capture even in low-light conditions. However, events captured at night exhibit differences in patterns compared to events captured during the day, causing performance degradation when using event-based algorithms trained on only day events for night scenarios. To overcome the limitation, I first tackle day-to-night translation in the event modality within an unpaired setting. To this end, I propose a Schrödinger Bridge diffusion model that effectively learns the mapping function from one domain to another, tailored for day-to-night event translation. Throughout the translation, wavelet decomposition is applied to analyze shared and distinct features between day and night events, trying to preserve shared elements while transporting differences. The temporally disentangled encoder is also designed which explicitly separates the event features and the temporal dimension. Introducing temporal contrastive learning helps maintain temporal order in events during the translation process. To validate the efficacy of the proposed methodology, I redesign metrics for evaluating events translated in an unpaired setting, aligning them with the event modality for the first time and subsequently justifying the metrics. The results obtained from the metrics illustrate the superior performance of the proposed approach compared to alternative methods. Lastly, through event translation, I facilitate downstream networks trained by incorporating labeled day events alongside the translated synthetic night events. This approach effectively mitigates the performance degradation of applying real night events to the task.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subject이벤트 카메라▼a낮에서 밤으로의 전환▼a쌍을 이루지 않는 데이터 간 전환▼a확산 모델▼a슈뢰딩거 브리지-
dc.subjectSchrodinger bridge-
dc.subjectEvent camera▼aday-to-night translation▼aunpaired translation▼adiffusion-
dc.titleDiffusion Schrodinger bridge for unpaired day-to-night event translation-
dc.title.alternative슈뢰딩거 브리지 기반 확산 모델을 이용한 쌍을 이루지 않는 낮에서 밤으로의 이벤트 전환-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :기계공학과,-
dc.contributor.alternativeauthorYoon, Kuk-Jin-
Appears in Collection
ME-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0