Related papers: A Preprocessing Framework for Video Machine Vision…
Recent advances in deep generative modeling have enabled efficient modeling of high dimensional data distributions and opened up a new horizon for solving data compression problems. Specifically, autoencoder based learned image or video…
With the increasing use of neural network (NN)-based computer vision applications that process image and video data as input, interest has emerged in video compression technology optimized for computer vision tasks. In fact, given the…
An ever increasing amount of our digital communication, media consumption, and content creation revolves around videos. We share, watch, and archive many aspects of our lives through them, all of which are powered by strong video…
Recently, learned video compression has drawn lots of attention and show a rapid development trend with promising results. However, the previous works still suffer from some criticial issues and have a performance gap with traditional…
This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Coding for Machines (FCM). This standard aims at providing inter-operable compressed…
Good quality video coding for low bit-rate applications is important for transmission over narrow-bandwidth channels and for storage with limited memory capacity. In this work, we develop a previous analysis for image compression at low…
As generative technologies advance, visual content has evolved into a complex mix of natural and AI-generated images, driving the need for more efficient coding techniques that prioritize perceptual quality. Traditional codecs and learned…
We show how transformers can be used to vastly simplify neural video compression. Previous methods have been relying on an increasing number of architectural biases and priors, including motion prediction and warping operations, resulting…
Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing, e.g., in distributed applications, coding methods must…
We propose sandwiching standard image and video codecs between pre- and post-processing neural networks. The networks are jointly trained through a differentiable codec proxy to minimize a given rate-distortion loss. This sandwich…
In this paper we present a a deep generative model for lossy video compression. We employ a model that consists of a 3D autoencoder with a discrete latent space and an autoregressive prior used for entropy coding. Both autoencoder and prior…
In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts such as blocking, ringing etc. Existing learned neural…
Classical video coding for satisfying humans as the final user is a widely investigated field of studies for visual content, and common video codecs are all optimized for the human visual system (HVS). But are the assumptions and…
Today, many image coding scenarios do not have a human as final intended user, but rather a machine fulfilling computer vision tasks on the decoded image. Thereby, the primary goal is not to keep visual quality but maintain the task…
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems…
Deep video compression has made significant progress in recent years, achieving rate-distortion performance that surpasses that of traditional video compression methods. However, rate control schemes tailored for deep video compression have…
One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to the human visual system. Despite this potential, a perceptual yet…
Machines are increasingly becoming the primary consumers of visual data, yet most deployments of machine-to-machine systems still rely on remote inference where pixel-based video is streamed using codecs optimized for human perception.…
Optimized for pixel fidelity metrics, images compressed by existing image codec are facing systematic challenges when used for visual analysis tasks, especially under low-bitrate coding. This paper proposes a visual analysis-motivated…
Recent deep-learning-based video compression methods brought coding gains over conventional codecs such as AVC and HEVC. However, learning-based codecs generally require considerable computation time and model complexity. In this paper, we…