Download presentation
Presentation is loading. Please wait.
Published byBrian Haslam Modified over 10 years ago
1
Removing Partial Blur in a Single Image Shengyang Dai and Ying Wu EECS Department, Northwestern University, Evanston, IL 60208, USA 2009CVPR
2
Outline Introduction Generation model of partial blur ◦ The two-layer model for a clear image ◦ Motion blur ◦ Out-of-focus blur ◦ Unified formulation of partial blurs Image recovery from partial degradation ◦ The objective function ◦ Initialization ◦ Recovering (F, B, α) Experiments Conclusion
3
Introduction Two key issues ◦ Partial blur estimation ◦ Partial deblurring
4
Generation model of partial blur(1/3) The two-layer model for a clear image ◦ I = F α + B(1 − α) Degraded image is the average over time F α : clear foreground component B(1 − α) : clear background component α : clear soft occlusion mask,α(x) ∈ [0, 1] for each pixel x
5
Generation model of partial blur(2/3) Motion blur ◦ Case 1: foreground object is moving static background, we have = 0, q = δ. ◦ Case 2: background is moving static foreground, we have = 0, p = δ. Out-of-focus blur ◦ Case 1: background layer is in focus foreground layer is out- of-focus ◦ Case 2: foreground layer is in focus background layer is out- of-focus
6
Generation model of partial blur(3/3) Unified formulation of partial blurs Either the foreground or background layer is not degraded ◦ p or q is the δ function
7
Image recovery from partial degradation(1/2) The objective function
8
Image recovery from partial degradation(1/2) Initialization ◦ extract the degraded occlusion mask by using a matting technique ◦ the degradation kernels p and q are estimated by analyzing both and ◦ iterate between F, B and α to obtain the final recovery
9
Experiments
12
Conclusion Removing partial blur from a single image input A two-layer image model ◦ foreground and background layers Enables high quality recovery and synthesis for real images
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.