BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Australia/Melbourne
X-LIC-LOCATION:Australia/Melbourne
BEGIN:DAYLIGHT
TZOFFSETFROM:+1000
TZOFFSETTO:+1100
TZNAME:AEDT
DTSTART:19721003T020000
RRULE:FREQ=YEARLY;BYMONTH=4;BYDAY=1SU
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:19721003T020000
TZOFFSETFROM:+1100
TZOFFSETTO:+1000
TZNAME:AEST
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240214T070247Z
LOCATION:Meeting Room C4.9+C4.10\, Level 4 (Convention Centre)
DTSTART;TZID=Australia/Melbourne:20231214T122500
DTEND;TZID=Australia/Melbourne:20231214T124000
UID:siggraphasia_SIGGRAPH Asia 2023_sess170_papers_517@linklings.com
SUMMARY:Low-Light Image Enhancement with Wavelet-based Diffusion Models
DESCRIPTION:Technical Papers\n\nHai Jiang (Sichuan University); Ao Luo and
  Haoqiang Fan (Megvii); Songchen Han (Sichuan University); and Shuaicheng 
 Liu (University of Electronic Science and Technology of China, Megvii)\n\n
 Diffusion models have achieved promising results in image restoration task
 s, yet suffer from time-consuming, excessive computational resource consum
 ption, and unstable restoration. To address these issues, we propose a rob
 ust and efficient Diffusion-based Low-Light image enhancement approach, du
 bbed DiffLL. Specifically, we present a wavelet-based conditional diffusio
 n model (WCDM) that leverages the generative power of diffusion models to 
 produce results with satisfactory perceptual fidelity. Additionally, it al
 so takes advantage of the strengths of wavelet transformation to greatly a
 ccelerate inference and reduce computational resource usage without sacrif
 icing information. To avoid chaotic content and diversity, we perform both
  forward diffusion and denoising in the training phase of WCDM, enabling t
 he model to achieve stable denoising and reduce randomness during inferenc
 e. Moreover, we further design a high-frequency restoration module (HFRM) 
 that utilizes the vertical and horizontal details of the image to compleme
 nt the diagonal information for better fine-grained restoration. Extensive
  experiments on publicly available real-world benchmarks demonstrate that 
 our method outperforms the existing state-of-the-art methods both quantita
 tively and visually, and it achieves remarkable improvements in efficiency
  compared to previous diffusion-based methods. In addition, we empirically
  show that the application for low-light face detection also reveals the l
 atent practical values of our method. Code is available at https://github.
 com/JianghaiSCU/Diffusion-Low-Light.\n\nRegistration Category: Full Access
 \n\nSession Chair: Xiangyu Xu (Xi'an Jiaotong University)
URL:https://asia.siggraph.org/2023/full-program?id=papers_517&sess=sess170
END:VEVENT
END:VCALENDAR