Presentation

<
LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography
SessionImaging, Video, and HDR
DescriptionMaster the night with LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography. Merging flare disentanglement and generative diffusion, our framework conquers entangled degradations. LUCID unlocks continuous control over global illumination and light source scale, enabling the brightening of deep shadows while strictly preventing light pollution.
Authors
Tingyu Yang
Shanghai Jiao Tong University
Yuan Cheng
Shanghai Jiao Tong University
Xiaoyun Yuan
Shanghai Jiao Tong University
Event Type
Technical Paper
TimeThursday, 23 July 20262:10pm - 2:20pm PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20262:00pm - 3:30pm PDTRoom 408 B
Keywords
Generative AI
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationLucky High Dynamic Range Smartphone Imaging
Similar Presentations
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization
Just-Dub-It: Video dubbing via Joint Audio-Visual Diffusion