Depth-Aware Image Compositing Model for Parallax Camera Motion Blur
This addresses camera motion blur issues in computer vision applications, but it is incremental as it builds on existing blur modeling and deblurring techniques.
The paper tackled the problem of depth-dependent spatially varying blur from parallax camera motion by proposing an Image Compositing Blur (ICB) model that generates realistic blur from a single image, depth map, and camera trajectory, and used it with an MLP to learn sharp representations, achieving competitive deblurring results.
Camera motion introduces spatially varying blur due to the depth changes in the 3D world. This work investigates scene configurations where such blur is produced under parallax camera motion. We present a simple, yet accurate, Image Compositing Blur (ICB) model for depth-dependent spatially varying blur. The (forward) model produces realistic motion blur from a single image, depth map, and camera trajectory. Furthermore, we utilize the ICB model, combined with a coordinate-based MLP, to learn a sharp neural representation from the blurred input. Experimental results are reported for synthetic and real examples. The results verify that the ICB forward model is computationally efficient and produces realistic blur, despite the lack of occlusion information. Additionally, our method for restoring a sharp representation proves to be a competitive approach for the deblurring task.