Depth-Aware Image Compositing Model for Parallax Camera Motion Blur

German F. TorresJoni-Kristian K\"am\"ar\"ainen

Mar 2023

摘要

Camera motion introduces spatially varying blur due to the depth changes inthe 3D world. This work investigates scene configurations where such blur isproduced under parallax camera motion. We present a simple, yet accurate, ImageCompositing 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 acoordinate-based MLP, to learn a sharp neural representation from the blurredinput. Experimental results are reported for synthetic and real examples. Theresults verify that the ICB forward model is computationally efficient andproduces realistic blur, despite the lack of occlusion information.Additionally, our method for restoring a sharp representation proves to be acompetitive approach for the deblurring task.

展开全部

图表提取

论文十问

参考文献

被引用

提问与回答

暂无人提供速读十问回答

被引用

笔记

问答

领域