Related papers: COIN++: Neural Compression Across Modalities
Implicit neural representations (INR) have gained increasing attention in representing 3D scenes and images, and have been recently applied to encode videos (e.g., NeRV, E-NeRV). While achieving promising results, existing INR-based methods…
This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the…
Studying the solar system and especially the Sun relies on the data gathered daily from space missions. These missions are data-intensive and compressing this data to make them efficiently transferable to the ground station is a twofold…
Neural Machine Translation (NMT) is resource intensive. We design a quantization procedure to compress NMT models better for devices with limited hardware capability. Because most neural network parameters are near zero, we employ…
Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…
Compression technology is essential for efficient image transmission and storage. With the rapid advances in deep learning, images are beginning to be used for image recognition as well as for human vision. For this reason, research has…
Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened…
The latent representation in learned image compression encompasses channel-wise, local spatial, and global spatial correlations, which are essential for the entropy model to capture for conditional entropy minimization. Efficiently…
Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations. It offers a more immersive perception than classic 2D images but at the cost of huge data…
This paper proposes a visual encryption method to ensure the confidentiality of digital images. The model used is based on an autoencoder using aConvolutional Neural Network (CNN) to ensure the protection of the user data on both the sender…
We present a perceptually-driven video compression framework integrating implicit neural representations (INRs) and pre-trained video diffusion models to address the extremely low bitrate regime (<0.05 bpp). Our approach exploits the…
The field of video compression has developed some of the most sophisticated and efficient compression algorithms known in the literature, enabling very high compressibility for little loss of information. Whilst some of these techniques are…
With the increasing consumption of 3D displays and virtual reality, multi-view video has become a promising format. However, its high resolution and multi-camera shooting result in a substantial increase in data volume, making storage and…
Deep Neural Networks reached state-of-the-art performance across numerous domains, but this progress has come at the cost of increasingly large and over-parameterized models, posing serious challenges for deployment on resource-constrained…
Deep variational autoencoders for image and video compression have gained significant attraction in the recent years, due to their potential to offer competitive or better compression rates compared to the decades long traditional codecs…
In this paper, a hybrid video compression framework is proposed that serves as a demonstrative showcase of deep learning-based approaches extending beyond the confines of traditional coding methodologies. The proposed hybrid framework is…
Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design…
The rapid growth of the big neural network models puts forward new requirements for lightweight network representation methods. The traditional methods based on model compression have achieved great success, especially VQ technology which…
Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word…
Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant…