相关论文: Perceptual Quality Improvement in Videoconferencin…
In recent years, AI generative models have made remarkable progress across various domains, including text generation, image generation, and video generation. However, assessing the quality of text-to-video generation is still in its…
Neural network-based methods have recently demonstrated state-of-the-art results on image synthesis and super-resolution tasks, in particular by using variants of generative adversarial networks (GANs) with supervised feature losses.…
In this paper, we propose a novel attribute-guided cross-resolution (low-resolution to high-resolution) face recognition framework that leverages a coupled generative adversarial network (GAN) structure with adversarial training to find the…
Although there have been notable advancements in video compression technologies in recent years, banding artifacts remain a serious issue affecting the quality of compressed videos, particularly on smooth regions of high-definition videos.…
This work focuses on low bitrate video streaming scenarios (e.g. 50 - 200Kbps) where the video quality is severely compromised. We present a family of novel deep generative models for enhancing perceptual video quality of such streams by…
Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder…
This paper targets to explore the inter-subject variations eliminated facial expression representation in the compressed video domain. Most of the previous methods process the RGB images of a sequence, while the off-the-shelf and valuable…
Despite success on a wide range of problems related to vision, generative adversarial networks (GANs) often suffer from inferior performance due to unstable training, especially for text generation. To solve this issue, we propose a new…
Virtual reality systems today cannot yet stream immersive, retina-quality virtual reality video over a network. One of the greatest challenges to this goal is the sheer data rates required to transmit retina-quality video frames at high…
Generative neural image compression supports data representation at extremely low bitrate, synthesizing details at the client and consistently producing highly realistic images. By leveraging the similarities between quantization error and…
Deep neural networks for image quality enhancement typically need large quantities of highly-curated training data comprising pairs of low-quality images and their corresponding high-quality images. While high-quality image acquisition is…
Packet loss is a major cause of voice quality degradation in VoIP transmissions with serious impact on intelligibility and user experience. This paper describes a system based on a generative adversarial approach, which aims to repair the…
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…
Video conferencing has caught much more attention recently. High fidelity and low bandwidth are two major objectives of video compression for video conferencing applications. Most pioneering methods rely on classic video compression codec…
Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional…
While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled framework to simultaneously mitigate two fundamental issues in…
DeepFakes are synthetic videos generated by swapping a face of an original image with the face of somebody else. In this paper, we describe our work to develop general, deep learning-based models to classify DeepFake content. We propose a…
We introduce a new encoder-decoder GAN model, FutureGAN, that predicts future frames of a video sequence conditioned on a sequence of past frames. During training, the networks solely receive the raw pixel values as an input, without…
To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can…
Person search has recently been a challenging task in the computer vision domain, which aims to search specific pedestrians from real cameras.Nevertheless, most surveillance videos comprise only a handful of images of each pedestrian, which…