Encoding algorithms: Netflix chooses Capacités and LS2N

Accessibility has driven the success of streaming video on demand (SVOD), and so have algorithms for recommendation and image compression. Netflix, a pioneer in the field, bet early on these algorithmic innovations and invested in state-of-the-art encoding techniques. This Californian SVOD giant noticed the research that Capacités and the LS2N (Digital Sciences Laboratory of Nantes) had conducted in AI and visual perception modeling and asked them to work on optimizing its algorithms. The goal was to compress the images without reducing the users’ perceived quality.

In a nutshell

Key words

sensorial perceptionalgorithmartificial intelligenceuser experiencevideo compression
Visual perception testing and modeling to optimize video encoding algorithms

Netflix wanted to improve its encoding algorithms in order to reduce video size further and increase speed. The company asked experts from Capacités and LS2N in Nantes to research how to decrease file sizes without altering the image quality perceived by the human eye.
The expert analysts of human image perception began by conducting a large-scale, subjective testing campaign. They developed a procedure in which several hundred participants viewed miscellaneous videos and rated their image quality. The experts then altered the videos’ appearance based on these ratings before submitting them to the next testers. This sequence was repeated multiple times, and each rating determined the following modifications.

In this type of visual perception study, experts can equip testers with an eye-tracking system that records their eye movement as they watch videos. They can then pinpoint image areas that capture attention and retain them during compression.
The results of the tests and analyses were modeled. Then they were used to optimize the encoding algorithms and to help Netflix teams choose the ideal compression format.
Incidentally, this research led to developing innovative algorithms that optimize data collection in subjective testing.


To successfully complete this project, the Capacités’ experts benefited from support and technical equipment from the LS2N laboratory (Digital Sciences Laboratory), joint research unit of Université de Nantes, Centrale Nantes engineering school, Inria, IMT Atlantique and CNRS (The French National Centre for Scientific Research).

Share this article with #ReadyOrNot


These projects may also interest you

Digital / AI

Facebook chooses Capacités to optimize video encoding

Facebook chose experts in visual perception at Capacités and the LS2N laboratory in Nantes to adapt its automatic encoding process to this new video content.

Read this success story

Composites testing for the aerospace industry

Composite materials’ behavior must comply with set standards for use in the aerospace industry, as defined by The National Centre for Space Studies (CNES, Centre National d’Etudes Spatiales). The verification process includes advanced mechanical tests that require specialized expertise in the mechanical behavior of materials. A leading player in the aerospace industry chose to collaborate with Capacités’ engineers to conduct measurements for u…

Read this success story

Enzymes at the Heart of Cell Therapy

A company that manufactures pharmaceutical grade hyaluronic acid contacted Capacités’ enzyme engineering experts: the company aims at developing a new deacetylation process which keeps overall polymer structure while increasing its interactions with stem cells.

Read this success story
Sea / ​​environment

L’Oréal and Capacités break new ground in evaluating biodegradability

L’Oréal called upon the experts at the GEPEA Laboratory and Capacités in order to assist in bridging this methodological gap. The resulting new process has served to assist L’Oréal in developing methods for evaluating the biodegradability of their products, thus allowing them to better adhere to the strict regulatory requirements.

Read this success story

This site uses cookies and gives you control over what you want to enable