Unified Colour Appearance Model based on Deep Learning

Huawei Nice Research Centre (France), in collaboration with Justus-Liebig-Universität Gießen (Germany), invites applications from qualified master's students for a six-month internship focused on enhancing colour appearance models in captured images.

Preferred Dates: Starting January-April 2025 for six months

Location: The Huawei Nice Research Centre located in Sophia Antipolis, South of France

Supervisors: Dr. Joseph Meehan (Huawei Research Centre) and Dr. Arash Akbarinia (University of Giessen)

About the company:
Huawei Technologies is a leading global information and communications technology (ICT) solutions provider. Driven by a commitment to sound operations, ongoing innovation, and open collaboration, we have established a competitive ICT portfolio of end-to-end solutions in telecom and enterprise networks, devices, and cloud technology and services. Our ICT solutions, products, and services are used in more than 170 countries and regions, serving over one-third of the world's population. With 180,000 employees, Huawei is committed to enabling the future information society, and building a Better Connected World. Huawei ranked 83th on the Global Fortune 500 based on its revenue in 2016. In 2016, the company’s revenue reached approximately USD 75.1 billion, with a 32% increase YOY and a solid increase in profits and cash flow.
As part of its overall investment strategy, Huawei supports innovation and contributions to the development of the economy in the countries where the group operates. Convinced that Europe and France in particular have a leading role to play on the world digital scene, Huawei is involved in the development of the digital sector and supports research and development in Europe. Huawei already has many R&D centers in place to meet market expectations.
The definition and realization of the Image Signal Processor (ISP) for the smartphone camera is one of the principal research domains at the Huawei Nice Research Center in Sophia Antipolis.
With the fast evolution of smartphone camera technologies and application scenarios, the ISP is becoming an increasingly crucial and complex component, and image processing algorithms are constantly updated as research makes progress and creates possibilities for new camera features.

Project Overview:
This project aims to refine the process of converting raw sensory data from cameras into visually appealing RGB images. This involves developing an integrated imaging framework that leverages  artificial intelligence and deep neural networks (DNN) to enhance the subjective experience of  amateur photographers using automatic photo capturing on mobile devices with learnable colour  appearance models [1, 2]. User sees “real” image and “processed” image using the Microsoft Hololens. Based on user feedback on preferences the colour model is updated (i.e. DNN CAM is
updated).
 

Key Responsibilities:
● Programming Psychophysical Experiments: Develop experiments using Augmented Reality (AR) glasses 
(Microsoft Hololens) and off-the-shelf SDKs. Proficiency in C++/C# and python is required.
● Deep Learning Implementation: Apply state-of-the-art deep learning methods.

Requirements:
● Bachelor of Science in Computer Science or related fields.
● Proficiency in C++/C# and Python programming language.
● Familiarity with deep learning libraries like PyTorch.
● The candidate should have the right to work in France.
 

References

[1] Fairchild, Mark D. Color appearance models. John Wiley & Sons, 2013.
[2] Fairchild, Mark D., and David R. Wyble. "hdr-CIELAB and hdr-IPT: Simple models for describing the color of high-dynamic-range and wide-color-gamut images." Color and Imaging Conference. Vol. 18. Society of Imaging Science and Technology, 2010.

2nd year of Masters or equivalent/PhD student