Copy-and-Paste Networks for Deep Video Inpainting
This addresses video completion and enhancement for applications like video editing and autonomous driving, representing a novel method for a known bottleneck.
The paper tackles video inpainting by proposing a deep learning framework that copies content from reference frames to fill missing regions, achieving visually pleasing results with faster runtime than state-of-the-art methods. It also applies this technique to enhance over/under exposed frames, improving lane detection accuracy on road videos.
We present a novel deep learning based algorithm for video inpainting. Video inpainting is a process of completing corrupted or missing regions in videos. Video inpainting has additional challenges compared to image inpainting due to the extra temporal information as well as the need for maintaining the temporal coherency. We propose a novel DNN-based framework called the Copy-and-Paste Networks for video inpainting that takes advantage of additional information in other frames of the video. The network is trained to copy corresponding contents in reference frames and paste them to fill the holes in the target frame. Our network also includes an alignment network that computes affine matrices between frames for the alignment, enabling the network to take information from more distant frames for robustness. Our method produces visually pleasing and temporally coherent results while running faster than the state-of-the-art optimization-based method. In addition, we extend our framework for enhancing over/under exposed frames in videos. Using this enhancement technique, we were able to significantly improve the lane detection accuracy on road videos.