Related papers: Invertible Image Rescaling
To fit diverse display and bandwidth constraints, high-frame-rate videos are temporally downscaled to low-frame-rate (LFR) and later upscaled, requiring joint optimization for effective frame-rate rescaling. However, existing methods…
Image restoration is essential for enhancing degraded images across computer vision tasks. However, most existing methods address only a single type of degradation (e.g., blur, noise, or haze) at a time, limiting their real-world…
In the recent years, there has been a significant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of…
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel. To improve real world…
Recently, the power of unconditional image synthesis has significantly advanced through the use of Generative Adversarial Networks (GANs). The task of inverting an image into its corresponding latent code of the trained GAN is of utmost…
Implicit Neural Representation (INR) has been emerging in computer vision in recent years. It has been shown to be effective in parameterising continuous signals such as dense 3D models from discrete image data, e.g. the neural radius field…
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully…
Over the past decades, a large number of techniques have emerged in modern imaging systems to capture the exact information of the original scene regardless of shake, motion, lighting conditions and etc., These developments have…
We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the…
While vision transformers achieve significant breakthroughs in various image restoration (IR) tasks, it is still challenging to efficiently scale them across multiple types of degradations and resolutions. In this paper, we propose…
In the practical applications of computed tomography imaging, the projection data may be acquired within a limited-angle range and corrupted by noises due to the limitation of scanning conditions. The noisy incomplete projection data…
Inversion by Direct Iteration (InDI) is a new formulation for supervised image restoration that avoids the so-called "regression to the mean" effect and produces more realistic and detailed images than existing regression-based methods. It…
Image inversion is a fundamental task in generative models, aiming to map images back to their latent representations to enable downstream applications such as editing, restoration, and style transfer. This paper provides a comprehensive…
Super-resolution (SR) has traditionally been based on pairs of high-resolution images (HR) and their low-resolution (LR) counterparts obtained artificially with bicubic downsampling. However, in real-world SR, there is a large variety of…
Nowadays, panoramic images can be easily obtained by panoramic cameras. However, when the panoramic camera orientation is tilted, a non-upright panoramic image will be captured. Existing upright adjustment models focus on how to estimate…
The last decades are marked by massive and diverse image data, which shows increasingly high resolution and quality. However, some images we obtained may be corrupted, affecting the perception and the application of downstream tasks. A…
Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition. However, they face notable challenges in performance and computational efficiency when dealing with real-world, multi-scale…
Custom and natural lighting conditions can be emulated in images of the scene during post-editing. Extraordinary capabilities of the deep learning framework can be utilized for such purpose. Deep image relighting allows automatic photo…
While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic manner, which is known to produce a blurry SR image. In…
The problem of restoration of digital images from their degraded measurements plays a central role in a multitude of practically important applications. A particularly challenging instance of this problem occurs in the case when the…