If you have ever watched a television show or live event or enjoyed a movie in VOD on your phone or tablet, this experience was likely brought to you through an Ateme solution. 

We are Ateme (PARIS: ATEME). We are the video delivery leader helping leading content providers, service providers and pure streaming players boost their engagement, acquire new viewers, and create new sources of revenues. Leveraging our continuous investment in R&D and innovation, we empower our customers to deliver a high quality of experience on any screen. 

Delivering video experiences also has an impact on our world. That’s why our multiple award-winning engineering teams design efficient and flexible solutions that cut waste, with no compromise on quality. So that viewers can enjoy their unique experiences – and the world we live in – well into the future. 

Thanks to a strong CSR policy that reinforces our mission to “Make the entertainment and video experience captivating, greener, and accessible to everyone,” we strive every day to build a better and more sustainable future for our planet, our people, and our ecosystem. 

At Ateme, we value innovation, collaboration, empowerment, agility, and everyone’s contributions. We offer cross-culture enrichment thanks to employees of 30 different nationalities. We consider the globe as our playground and we facilitate mobility internationally, especially in our offices in France, Sao Paulo, Denver, New York and Singapore. 

Be part of our team and join our fantastic journey! 

Main activities : 

Subject: Exploring quality metrics for Neural Video Codec 

Nowadays, our societies are highly dependent on digital video broadcast. An industry which is itself highly restricted by the bandwidth for distribution of a tremendous amount of video over different transportation means (Terrestrial, Satellite, Internet, mobile). The increase in video consumption leads to a massive usage of computational resources in datacenters. To deal with this increase, several video compression algorithms have been standardized such as Advanced Video Coding (AVC)[1], High Efficiency Video Coding (HEVC) [2] and the latest video codec Versatile Video Coding (VVC)[3].  

However, In the past few years, these traditional codecs have been challenged by neural video codecs. In fact, end-to-end neural image and video coding approaches [4, 5, 6] have shown promising results, making them compete with HEVC and VVC, in terms of compression efficiency. These video coding models minimize a loss function that includes a distortion term between source and decoding frames. Currently, classic metrics are used such as MSE/ PSNR and MS-SSIM. The goal of this internship is to explore additional quality metrics. Several categories exist in the literature such as Full-reference, perceptual, and blind metrics. The idea is to integrate them into both the training and the evaluation process of the video coding model, particularly, within the loss function and the quality assessment computations. 

This internship will consist of following phases:  

1. State-of-the art of video quality metrics. 

1. Introduction, understanding, and operating with the existing neural video codec.  

1. Integration of selected quality metrics in the training and evaluation process of the neural codec.  

1. Analysis and comparison of different models across multiple metrics.  

In all above phases, the candidate will constantly interact with his/her colleagues to benefit from their knowledge and experience. Noteworthy of precising that, based on the profile of the candidate, the internship orientation might be adjusted. 

References : 

[1] T. Wiegand, GJ Sullivan, G. Bjontegaard, and A Luthra. 2003. Overview of the H. 264/AVC video coding standard. IEEE Transactions on circuits and systems for video technology 13, 7 (2003), 560–576. 

[2] G. Sullivan, J. Ohm, W. Han, and T. Wiegand. 2012. Overview of the high efficiency video coding (HEVC) standard. IEEE Transactions on circuits and systems for video technology 22, 12 (2012), 1649–1668 

[3] G. Sullivan et J. R. Ohm, «Versatile video coding Towards the next generation of video compression,» chez Picture Coding Symposium,, 2018 

[4] B. L. Y. L. Jiahao Li, «Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression,» Proceedings of the 30th ACM International Conference on Multimedia, p. 1503–1511, 2022. 

[5] J. Li, B. Li et Y. Lu, «Neural video compression with diverse contexts.,» chez CVPR, 2023. 

[6] H. M. Kwan, G. Gao, F. Zhang, A. Gower, Bull et D, «HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation.,» chez Advances in Neural Information Processing Systems, 2024. 

About the candidate: 

• Last-year student of engineering school program or master’s in computer science or electrical engineering. 

• Excellent python programming skills. 

• Hand-on experience with neural networks and libraries such as TensorFlow, PyTorch etc. 

• Ability to read and understand academic papers in the domain of image and video processing. 

• Being familiar with video compression algorithms is a plus. 

• Fluent in English.  

Location: The position is based in Rennes (35) 

Benefits: 1500€ gross + Ticket restaurant + Reimbursement of transportation fees + possibility of recruitment (CDI) or CIFRE thesis 

Contacts:  jobs@ateme.com 

To find out more about our company, do not hesitate to visit our website: www.ateme.com