Related papers: Neural Compression-Based Feature Learning for Vide…
A learning-based framework for representation of domain-specific images is proposed where joint compression and denoising can be done using a VQ-based multi-layer network. While it learns to compress the images from a training set, the…
Neural compression offers a domain-agnostic approach to creating codecs for lossy or lossless compression via deep generative models. For sequence compression, however, most deep sequence models have costs that scale with the sequence…
A long-standing topic in artificial intelligence is the effective recognition of patterns from noisy images. In this regard, the recent data-driven paradigm considers 1) improving the representation robustness by adding noisy samples in…
Learned video compression methods have gained a variety of interest in the video coding community since they have matched or even exceeded the rate-distortion (RD) performance of traditional video codecs. However, many current…
While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images. In a similar spirit, we view…
Although deep convolutional neural network has been proved to efficiently eliminate coding artifacts caused by the coarse quantization of traditional codec, it's difficult to train any neural network in front of the encoder for gradient's…
Video reconstruction from a single motion-blurred image is a challenging problem, which can enhance the capabilities of existing cameras. Recently, several works addressed this task using conventional imaging and deep learning. Yet, such…
Small compression noises, despite being transparent to human eyes, can adversely affect the results of many image restoration processes, if left unaccounted for. Especially, compression noises are highly detrimental to inverse operators of…
In this paper, we present a novel robust framework for low-level vision tasks, including denoising, object removal, frame interpolation, and super-resolution, that does not require any external training data corpus. Our proposed approach…
Humans do not perceive all parts of a scene with the same resolution, but rather focus on few regions of interest (ROIs). Traditional Object-Based codecs take advantage of this biological intuition, and are capable of non-uniform allocation…
Inspired by the facts that retinal cells actually segregate the visual scene into different attributes (e.g., spatial details, temporal motion) for respective neuronal processing, we propose to first decompose the input video into…
The emergence of Neural Radiance Fields (NeRF) has greatly impacted 3D scene modeling and novel-view synthesis. As a kind of visual media for 3D scene representation, compression with high rate-distortion performance is an eternal target.…
Video Denoising is one of the fundamental tasks of any videoprocessing pipeline. It is different from image denoising due to the tem-poral aspects of video frames, and any image denoising approach appliedto videos will result in flickering.…
Learning-based methods have enabled the recovery of a video sequence from a single motion-blurred image or a single coded exposure image. Recovering video from a single motion-blurred image is a very ill-posed problem and the recovered…
There has been a growing trend in compressing and transmitting videos from terminals for machine vision tasks. Nevertheless, most video coding optimization method focus on minimizing distortion according to human perceptual metrics,…
The ever-growing size of neural networks poses serious challenges on resource-constrained devices, such as embedded sensors. Compression algorithms that reduce their size can mitigate these problems, provided that model performance stays…
Noise robustness remains a critical challenge for deploying neural speech codecs in real-world acoustic scenarios where background noise is often inevitable. A key observation we make is that even slight input noise perturbations can cause…
The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video…
Neural speech codecs have been widely used in audio compression and various downstream tasks. Current mainstream codecs are fixed-frame-rate (FFR), which allocate the same number of tokens to every equal-duration slice. However, speech is…
Quantization is one of the core components in lossy image compression. For neural image compression, end-to-end optimization requires differentiable approximations of quantization, which can generally be grouped into three categories:…