Organisation/Company: CNRS
Department: Institut de recherche en informatique et systèmes aléatoires
Research Field: Engineering, Computer science, Mathematics
Researcher Profile: First Stage Researcher (R1)
Country: France
Application Deadline: 31 Dec 2024 - 00:00 (UTC)
Type of Contract: Temporary
Job Status: Full-time
Hours Per Week: 35
Offer Starting Date: 1 Jan 2025
Is the job funded through the EU Research Framework Programme? Not funded by a EU programme
Is the Job related to staff position within a Research Infrastructure? No
Offer Description Research Topic: All the recent advances in video compression are due to an increase of the complexity: e.g., more tools and more freedom in the choice of parameters or fully deep learning-based algorithms. In such a context, the global energy cost due to video consumption can only explode, which is not compatible with the urgent need of energetic sobriety. Developing low-energetic video compression/decompression algorithms has been explored for a long time. However, most of the time, the achieved low complexity of the compression algorithms comes from the reduction of the capability of the video coder (e.g., less parameters to estimate, removing of some complex functionalities). Such approaches do not put in question the trade-off between complexity and video coding performance, and thus remain limited. In this project, we plan to investigate low complexity compression algorithms that are not low-cost versions of a complex algorithm. The proposed methodology is the following. We start from a complex learning-based coder as for example the auto-encoder-like architecture proposed in [1]. Such architectures are able to achieve outstanding performance, with, however a gigantic encoding and decoding complexity. Our goal is to investigate how to deduce from this trained network and its millions of parameters, some efficient features for low complexity compression. As an example, we can show that the set of non-linear operations involved in a deep convolutional neural architecture can be modeled as a linear operation once the input is fixed, like it is studied in [2,3]. The strength of the deep architecture resides in its ability to adjust this linear filter to the input. For our purpose, we will, on the contrary, investigate if some common features reside in these linear filters when the input is changed. These common features may constitute, for example, an efficient transform or partitioning operation that does not require anymore millions of parameters. In a nutshell, the intuition will be to take benefit of algorithms trained on a large set of images and to extract from them some common analysis tools.
[1] Fabian Mentzer, George D Toderici, Michael Tschannen, and Eirikur Agustsson. High-fidelity generative image compression. Advances in Neural Information Processing Systems, 33:11913–11924, 2020.
[2] Sreyas Mohan. Robust and Interpretable Denoising Via Deep Learning. PhD thesis, New York University, 2022.
[3] Sreyas Mohan, Zahra Kadkhodaie, Eero P Simoncelli, and Carlos Fernandez-Granda. Robust and interpretable blind image denoising via bias-free convolutional neural networks. arXiv preprint arXiv:1906.05478, 2019.
#J-18808-Ljbffr