BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250110T023312Z
LOCATION:Hall B7 (1)\, B Block\, Level 7
DTSTART;TZID=Asia/Tokyo:20241205T153100
DTEND;TZID=Asia/Tokyo:20241205T154300
UID:siggraphasia_SIGGRAPH Asia 2024_sess135_papers_733@linklings.com
SUMMARY:From Sim-to-Real: Toward General Event-based Low-light Frame Inter
 polation with Per-scene Optimization
DESCRIPTION:Technical Papers\n\nZiran Zhang (Zhejiang University, Shanghai
  Artificial Intelligence Laboratory); Yongrui Ma (Chinese University of Ho
 ng Kong, Shanghai Artificial Intelligence Laboratory); Yueting Chen (Zheji
 ang University); Feng Zhang (Shanghai Artificial Intelligence Laboratory);
  Jinwei Gu and Tianfan Xue (Chinese University of Hong Kong); and Shi Guo 
 (Shanghai Artificial Intelligence Laboratory)\n\nVideo Frame Interpolation
  (VFI) is important for video enhancement, frame rate up-conversion, and s
 low-motion generation. The introduction of event cameras, which capture pe
 r-pixel brightness changes asynchronously, has significantly enhanced VFI 
 capabilities, particularly for high-speed, nonlinear motions. However, the
 se event-based methods encounter challenges in low-light conditions, notab
 ly trailing artifacts and signal latency, which hinder their direct applic
 ability and generalization. Addressing these issues, we propose a novel pe
 r-scene optimization strategy tailored for low-light conditions. This appr
 oach utilizes the internal statistics of a sequence to handle degraded eve
 nt data under low-light conditions, improving the generalizability to diff
 erent lighting and camera settings. To evaluate its robustness in low-ligh
 t condition, we further introduce EVFI-LL, a unique RGB+Event dataset capt
 ured under low-light conditions. Our results demonstrate state-of-the-art 
 performance in low-light environments. Project page: https://openimagingla
 b.github.io/Sim2Real/.\n\nRegistration Category: Full Access, Full Access 
 Supporter\n\nLanguage Format: English Language\n\nSession Chair: Changjian
  Li (University of Edinburgh)
URL:https://asia.siggraph.org/2024/program/?id=papers_733&sess=sess135
END:VEVENT
END:VCALENDAR