Occlusion-Aware Video Deblurring with a New Layered Blur Model
This work addresses a specific limitation in video deblurring for scenes with occlusions, which is incremental but improves accuracy at boundaries.
The paper tackled the problem of video deblurring in scenes with occluding objects by proposing a new layered blur model that better represents interactions at occlusion boundaries, resulting in superior deblurring performance, especially at object boundaries, as demonstrated on synthetic and real videos.
We present a deblurring method for scenes with occluding objects using a carefully designed layered blur model. Layered blur model is frequently used in the motion deblurring problem to handle locally varying blurs, which is caused by object motions or depth variations in a scene. However, conventional models have a limitation in representing the layer interactions occurring at occlusion boundaries. In this paper, we address this limitation in both theoretical and experimental ways, and propose a new layered blur model reflecting actual blur generation process. Based on this model, we develop an occlusion-aware deblurring method that can estimate not only the clear foreground and background, but also the object motion more accurately. We also provide a novel analysis on the blur kernel at object boundaries, which shows the distinctive characteristics of the blur kernel that cannot be captured by conventional blur models. Experimental results on synthetic and real blurred videos demonstrate that the proposed method yields superior results, especially at object boundaries.