293 papers with code • 15 benchmarks • 13 datasets
Deblurring is a computer vision task that involves removing the blurring artifacts from images or videos to restore the original, sharp content. Blurring can be caused by various factors such as camera shake, fast motion, and out-of-focus objects, and can result in a loss of detail and quality in the captured images. The goal of deblurring is to produce a clear, high-quality image that accurately represents the original scene.
The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images.
In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges.
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks.
We present a new end-to-end generative adversarial network (GAN) for single image motion deblurring, named DeblurGAN-v2, which considerably boosts state-of-the-art deblurring efficiency, quality, and flexibility.
We propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i. e. temporal super-resolution).
In single image deblurring, the "coarse-to-fine" scheme, i. e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches.
Recent works on plug-and-play image restoration have shown that a denoiser can implicitly serve as the image prior for model-based methods to solve many inverse problems.