Related papers: Controlling Rate, Distortion, and Realism: Towards…

Conditional Generative Adversarial Networks (cGANs) have enabled controllable image synthesis for many vision and graphics applications. However, recent cGANs are 1-2 orders of magnitude more compute-intensive than modern recognition CNNs.…

Deep generative models have achieved conspicuous progress in realistic image synthesis with multifarious conditional inputs, while generating diverse yet high-fidelity images remains a grand challenge in conditional image generation. This…

With the great success of diffusion models in image generation, diffusion-based image compression is attracting increasing interests. However, due to the random noise introduced in the diffusion learning, they usually produce…

Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results…

This paper considers the problem of lossy neural image compression (NIC). Current state-of-the-art (sota) methods adopt uniform posterior to approximate quantization noise, and single-sample pathwise estimator to approximate the gradient of…

Compressed domain image classification performs classification directly on compressive measurements acquired from the single-pixel camera, bypassing the image reconstruction step. It is of great importance for extending high-speed object…

This paper outlines an end-to-end optimized lossy image compression framework using diffusion generative models. The approach relies on the transform coding paradigm, where an image is mapped into a latent space for entropy coding and, from…

We propose a unified Generative Adversarial Network (GAN) for controllable image-to-image translation, i.e., transferring an image from a source to a target domain guided by controllable structures. In addition to conditioning on a…

The popularity of high and ultra-high definition displays has led to the need for methods to improve the quality of videos already obtained at much lower resolutions. Current Video Super-Resolution methods are not robust to mismatch between…

Deep image denoising networks have achieved impressive success with the help of a considerably large number of synthetic train datasets. However, real-world denoising is a still challenging problem due to the dissimilarity between…

Sparse representation leads to an efficient way to approximately recover a signal by the linear composition of a few bases from a learnt dictionary, based on which various successful applications have been achieved. However, in the scenario…

Generative Adversarial Networks (GANs), though powerful, is hard to train. Several recent works (brock2016neural,miyato2018spectral) suggest that controlling the spectra of weight matrices in the discriminator can significantly improve the…

Static scene videos, such as surveillance feeds and videotelephony streams, constitute a dominant share of storage consumption and network traffic. However, both traditional standardized codecs and neural video compression (NVC) methods…

Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in recent studies. However, the adversarial attacks considered in…

Deep learning models have significantly improved the visual quality and accuracy on compressive sensing recovery. In this paper, we propose an algorithm for signal reconstruction from compressed measurements with image priors captured by a…

Compression is a standard procedure for making convolutional neural networks (CNNs) adhere to some specific computing resource constraints. However, searching for a compressed architecture typically involves a series of time-consuming…

Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates. Previous methods focus on using diffusion models as expressive…

Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the…

Deep learning's success has led to larger and larger models to handle more and more complex tasks; trained models can contain millions of parameters. These large models are compute- and memory-intensive, which makes it a challenge to deploy…

We propose a novel method for compressed sensing recovery using untrained deep generative models. Our method is based on the recently proposed Deep Image Prior (DIP), wherein the convolutional weights of the network are optimized to match…