FAst and energy efficient Learned image and video CompresiON

Project Information

FALCON

Grant agreement ID: 101022466

DOI

10.3030/101022466

Project closed

EC signature date 17 March 2021

Start date 1 March 2022

End date 29 February 2024

Funded under

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Total cost

€ 190 680,96

EU contribution

€ 190 680,96

Coordinated by

TAMPEREEN KORKEAKOULUSAATIO SR
Finland

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Peer reviewed articles (2)

Lightweight Multitask Learning for Robust JND Prediction using Latent Space and Reconstructed Frames

Author(s): Sanaz Nami, Farhad Pakdaman, Mahmoud Reza Hashemi, Shervin Shirmohammadi, Moncef Gabbouj
Published in: IEEE Transactions on Circuits and Systems for Video Technology, Issue Early Access, 2024, Page(s) 1-14, ISSN 1051-8215
Publisher: Institute of Electrical and Electronics Engineers
DOI: 10.1109/tcsvt.2024.3389988

MAMIQA: No-Reference Image Quality Assessment Based on Multiscale Attention Mechanism With Natural Scene Statistics

Author(s): Li Yu; Junyang Li; Farhad Pakdaman; Miaogen Ling; Moncef Gabbouj
Published in: IEEE Signal Processing Letters, Issue 30, 2023, Page(s) 588-592, ISSN 1558-2361
Publisher: IEEE
DOI: 10.1109/lsp.2023.3276645

Conference proceedings (5)

NCOD: Near-Optimum Video Compression for Object Detection

Author(s): Ardavan Elahi, Ali Falahati, Farhad Pakdaman, Mehdi Modarressi, Moncef Gabbouj
Published in: IEEE International Symposium on Circuits and Systems (ISCAS), Issue 2023, 2023, Page(s) 1-5
Publisher: IEEE
DOI: 10.1109/iscas46773.2023.10182205

MTJND: Multi-Task Deep Learning Framework for Improved JND Prediction

Author(s): Sanaz Nami, Farhad Pakdaman, Mahmoud Reza Hashemi, Shervin Shirmohammadi, Moncef Gabbouj
Published in: IEEE International Conference on Image Processing (ICIP), Issue 2023, 2023, Page(s) 1245-1249
Publisher: IEEE
DOI: 10.1109/icip49359.2023.10222099

Panoramic Image Inpainting with Gated Convolution and Contextual Reconstruction Loss

Author(s): Li Yu, Yanjun Gao, Farhad Pakdaman, Moncef Gabbouj
Published in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Issue 2024, 2024, Page(s) 4255-4259
Publisher: IEEE
DOI: 10.1109/icassp48485.2024.10446469

Comprehensive Complexity Assessment of Emerging Learned Image Compression on CPU and GPU

Author(s): Farhad Pakdaman, Moncef Gabbouj
Published in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Issue 2023, 2023, Page(s) 1-3
Publisher: IEEE
DOI: 10.1109/icassp49357.2023.10096046

Efficient Bitrate Ladder Construction using Transfer Learning and Spatio-Temporal Features

Author(s): Ali Falahati, Mohammad Karim Safavi, Ardavan Elahi, Farhad Pakdaman, Moncef Gabbouj
Published in: 13th Iranian/3rd International Conference on Machine Vision and Image Processing Conference (MVIP), Issue 2024, 2024, Page(s) 1-7
Publisher: IEEE
DOI: 10.1109/mvip62238.2024.10491154

Other (4)

Channel-wise Feature Decorrelation for Enhanced Learned Image Compression

Author(s): Farhad Pakdaman, Moncef Gabbouj
Published in: arXiv preprint, Issue 2024, 2024
Publisher: arxiv.org
DOI: 10.48550/arxiv.2403.10936

Joint End-to-End Image Compression and Denoising: Leveraging Contrastive Learning and Multi-Scale Self-ONNs

Author(s): Yuxin Xie, Li Yu, Farhad Pakdaman, Moncef Gabbouj
Published in: arXiv preprint, Issue 2024, 2024
Publisher: arxiv.org
DOI: 10.48550/arxiv.2402.05582

Perceptual Learned Image Compression via End-to-End JND-Based Optimization

Author(s): Farhad Pakdaman, Sanaz Nami, Moncef Gabbouj
Published in: arXiv preprint, Issue 2024, 2024
Publisher: arxiv.org
DOI: 10.48550/arxiv.2402.02836

Pixel-Wise Color Constancy via Smoothness Techniques in Multi-Illuminant Scenes

Author(s): Umut Cem Entok, Firas Laakom, Farhad Pakdaman, Moncef Gabbouj
Published in: arXiv preprint, Issue 2024, 2024
Publisher: arxiv.org
DOI: 10.48550/arxiv.2402.02922