Meet ApplyKite Twin, the application assistant that learns with you
Meet your Twin, it learns with you
Your Twin learns with you
Launch week codes:30% off annual Pro20% off monthly Pro
Ends in00h00m00s
Ends in00h00m00s
CNRS
Just Landed
1 days ago
Postdoctoral Researcher in Image Coding and Enhancement CNRS in France
Degree Level
Postdoc
Field of study
Computer Science
Funding
Available
Deadline
Dec 1, 2026
Country
France
University
CNRS
Apply for this position
Free with an ApplyKite account: the application link, the deadline in your tracker and a check of your fit.
Keywords
Suggested positions
About this position
This postdoctoral position is part of the EPERVIER project at CNRS and focuses on the development of new methods for image and video coding for both automatic analysis systems and human operators.
The successful candidate will work on machine-oriented compression: designing a coding solution that preserves the information most useful for artificial intelligence tasks such as object detection, classification, and localization of objects or people, while still enabling content reconstruction when human interpretation is needed.
The research will explore learned, adaptive and scalable coding architectures that can provide multiple levels of access from a single compressed representation. The aim is to organize the bitstream into successive layers, starting from a minimal representation for one or more machine tasks and extending to additional information that can improve other analysis tasks or support reconstruction for human viewing.
A major aspect of the project is the study of coding methods for embedded and drone-based transmission, where communication bandwidth, computational resources, energy consumption, and transmission conditions are constrained. The work is therefore positioned at the intersection of compression, computer vision, and efficient deployment on resource-limited platforms.
The position also examines how image enhancement methods can interact with coding when images are acquired in highly degraded conditions. In particular, the project will investigate whether restoration, denoising, and super-resolution can simultaneously improve compression efficiency and the performance of automatic vision tasks.
The recruited researcher will contribute to the study of learned compression for human and machine use, multi-task coding strategies, dynamic adaptation of coding to scene content and regions of interest, and objective functions balancing bitrate, perceptual distortion, and task performance.
Funding details
Available
What's required
No specific degree, GPA, language test, or other entry requirements are stated in the advert excerpt provided. The position seeks candidates able to study the state of the art in image and video coding, develop learned compression architectures, and work on computer-vision-oriented representations and enhancement methods.
How to apply
Apply through the official application page on Choisir le service public. Use the provided advert link to access the full listing and submit the required materials via the portal.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.