Zobrazeno 1 - 10
of 219
pro vyhledávání: '"Hannuksela, Miska"'
Autor:
Ahonen, Jukka I., Le, Nam, Zhang, Honglei, Hallapuro, Antti, Cricri, Francesco, Tavakoli, Hamed Rezazadegan, Hannuksela, Miska M., Rahtu, Esa
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 been design
Externí odkaz:
http://arxiv.org/abs/2401.10761
Autor:
Le, Nam, Zhang, Honglei, Cricri, Francesco, Youvalari, Ramin G., Tavakoli, Hamed Rezazadegan, Aksu, Emre, Hannuksela, Miska M., Rahtu, Esa
Publikováno v:
IEEE International Conference on Image Processing (ICIP), Bordeaux, France, 2022, pp. 3411-3415
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 quality is not dr
Externí odkaz:
http://arxiv.org/abs/2401.10732
Autor:
Zhang, Honglei, Cricri, Francesco, Tavakoli, Hamed Rezazadegan, Aksu, Emre, Hannuksela, Miska M.
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 (DCT) and
Externí odkaz:
http://arxiv.org/abs/2210.04112
Autor:
Santamaria, Maria, Vadakital, Vinod Kumar Malamal, Kondrad, Lukasz, Hallapuro, Antti, Hannuksela, Miska M.
Publikováno v:
2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)
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 deliver 6DoF im
Externí odkaz:
http://arxiv.org/abs/2206.02588
Publikováno v:
2021 IEEE Conference on Standards for Communications and Networking (CSCN), 2021, pp. 20-25
This paper provides an overview of the Omnidirectional Media Format (OMAF) standard, second edition, which has been recently finalized. OMAF specifies the media format for coding, storage, delivery, and rendering of omnidirectional media, including v
Externí odkaz:
http://arxiv.org/abs/2203.01183
Autor:
Zou, Nannan, Zhang, Honglei, Cricri, Francesco, Youvalari, Ramin G., Tavakoli, Hamed R., Lainema, Jani, Aksu, Emre, Hannuksela, Miska, Rahtu, Esa
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 architectural novel
Externí odkaz:
http://arxiv.org/abs/2112.08767
Autor:
Zhang, Honglei, Cricri, Francesco, Tavakoli, Hamed R., Zou, Nannan, Aksu, Emre, Hannuksela, Miska M.
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 achieve a higher
Externí odkaz:
http://arxiv.org/abs/2108.10551
Autor:
Zou, Nannan, Zhang, Honglei, Cricri, Francesco, Tavakoli, Hamed R., Lainema, Jani, Hannuksela, Miska, Aksu, Emre, Rahtu, Esa
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 time, the enco
Externí odkaz:
http://arxiv.org/abs/2007.16054
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 the specific
Externí odkaz:
http://arxiv.org/abs/2007.14267
Autor:
Zou, Nannan, Zhang, Honglei, Cricri, Francesco, Tavakoli, Hamed R., Lainema, Jani, Aksu, Emre, Hannuksela, Miska, Rahtu, Esa
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 compressing vi
Externí odkaz:
http://arxiv.org/abs/2004.09226