Miska M. Hannuksela
YOU?
Author Swipe
View article: L2C -- Learning to Learn to Compress
L2C -- Learning to Learn to Compress Open
In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference tim…
View article: NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines
NN-VVC: Versatile Video Coding boosted by self-supervisedly learned image coding for machines Open
The recent progress in artificial intelligence has led to an ever-increasing usage of images and videos by machine analysis algorithms, mainly neural networks. Nonetheless, compression, storage and transmission of media have traditionally …
View article: Bridging the Gap Between Image Coding for Machines and Humans
Bridging the Gap Between Image Coding for Machines and Humans Open
Image coding for machines (ICM) aims at reducing the bitrate required to represent an image while minimizing the drop in machine vision analysis accuracy. In many use cases, such as surveillance, it is also important that the visual qualit…
View article: Leveraging progressive model and overfitting for efficient learned image compression
Leveraging progressive model and overfitting for efficient learned image compression Open
Deep learning is overwhelmingly dominant in the field of computer vision and image/video processing for the last decade. However, for image and video compression, it lags behind the traditional techniques based on discrete cosine transform…
View article: Viewport-Dependent Delivery for Conversational Immersive Video
Viewport-Dependent Delivery for Conversational Immersive Video Open
Real-time immersive video has been an area of interest for the research and standardization community over the past few years. It has gained particular importance in the era of 5G services. 3GPP (Third Generation Partnership Project) Relea…
View article: Adaptation and Attention for Neural Video Coding
Adaptation and Attention for Neural Video Coding Open
Neural image coding represents now the state-of-the-art image compression approach. However, a lot of work is still to be done in the video domain. In this work, we propose an end-to-end learned video codec that introduces several architec…
View article: Omnidirectional MediA Format (OMAF): Toolbox for Virtual Reality Services
Omnidirectional MediA Format (OMAF): Toolbox for Virtual Reality Services Open
This paper provides an overview of the Omnidirectional Media Format (OMAF)\nstandard, second edition, which has been recently finalized. OMAF specifies the\nmedia format for coding, storage, delivery, and rendering of omnidirectional\nmedi…
View article: Coding of volumetric content with MIV using VVC subpictures
Coding of volumetric content with MIV using VVC subpictures Open
Storage and transport of six degrees of freedom (6DoF) dynamic volumetric visual content for immersive applications requires efficient compression. ISO/IEC MPEG has recently been working on a standard that aims to efficiently code and deli…
View article: Lossless Image Compression Using a Multi-Scale Progressive Statistical Model
Lossless Image Compression Using a Multi-Scale Progressive Statistical Model Open
Lossless image compression is an important technique for image storage and transmission when information loss is not allowed. With the fast development of deep learning techniques, deep neural networks have been used in this field to achie…
View article: Overview of the Neural Network Compression and Representation (NNR) Standard
Overview of the Neural Network Compression and Representation (NNR) Standard Open
3203
View article: The High-Level Syntax of the Versatile Video Coding (VVC) Standard
The High-Level Syntax of the Versatile Video Coding (VVC) Standard Open
Versatile Video Coding (VVC), a.k.a. ITU-T H.266 | ISO/IEC 23090-3, is the new generation video coding standard that has just been finalized by the Joint Video Experts Team (JVET) of ITU-T VCEG and ISO/IEC MPEG at its 19th meeting ending o…
View article: An Overview of Omnidirectional MediA Format (OMAF)
An Overview of Omnidirectional MediA Format (OMAF) Open
During recent years, there have been product launches and research for enabling immersive audio-visual media experiences. For example, a variety of head-mounted displays and 360° cameras are available in the market. To facilitate interoper…
View article: Efficient Adaptation of Neural Network Filter for Video Compression
Efficient Adaptation of Neural Network Filter for Video Compression Open
We present an efficient finetuning methodology for neural-network filters which are applied as a postprocessing artifact-removal step in video coding pipelines. The fine-tuning is performed at encoder side to adapt the neural network to th…
View article: Learning to Learn to Compress
Learning to Learn to Compress Open
In this paper we present an end-to-end meta-learned system for image compression. Traditional machine learning based approaches to image compression train one or more neural network for generalization performance. However, at inference tim…
View article: End-to-End Learning for Video Frame Compression with Self-Attention
End-to-End Learning for Video Frame Compression with Self-Attention Open
One of the core components of conventional (i.e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations. In this paper, we propose an end-to-end learned system for com…
View article: A Compression Objective and a Cycle Loss for Neural Image Compression
A Compression Objective and a Cycle Loss for Neural Image Compression Open
In this manuscript we propose two objective terms for neural image compression: a compression objective and a cycle loss. These terms are applied on the encoder output of an autoencoder and are used in combination with reconstruction losse…
View article: Compressing Weight-updates for Image Artifacts Removal Neural Networks
Compressing Weight-updates for Image Artifacts Removal Neural Networks Open
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact remova…
View article: Compressing Weight-updates for Image Artifacts Removal Neural Networks
Compressing Weight-updates for Image Artifacts Removal Neural Networks Open
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible. At encoder side, we fine-tune a pre-trained artifact remova…
View article: Video coding of dynamic 3D point cloud data
Video coding of dynamic 3D point cloud data Open
Video coding of dynamic 3D point cloud datasebastian schwarz, 1 nahid sheikhipour, 1,2 vida fakour sevom 2 and miska m. hannuksela 1 Due to the increased popularity of augmented (AR) and virtual (VR) reality experiences, the interest in re…
View article: A Compression Objective and a Cycle Loss for Neural Image Compression
A Compression Objective and a Cycle Loss for Neural Image Compression Open
In this manuscript we propose two objective terms for neural image compression: a compression objective and a cycle loss. These terms are applied on the encoder output of an autoencoder and are used in combination with reconstruction losse…
View article: Block-optimized Variable Bit Rate Neural Image Compression
Block-optimized Variable Bit Rate Neural Image Compression Open
In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with …