Intern, Filter banks classification

About InterDigital

InterDigital is a global research and development company focused primarily on wireless, video, artificial intelligence ("AI"), and related technologies. We design and develop foundational technologies that enable connected, immersive experiences in a broad range of communications and entertainment products and services. We license our innovations worldwide to companies providing such products and services, including makers of wireless communications devices, consumer electronics, IoT devices, cars and other motor vehicles, and providers of cloud-based services such as video streaming. As a leader in wireless technology, our engineers have designed and developed a wide range of innovations that are used in wireless products and networks, from the earliest digital cellular systems to 5G and today's most advanced Wi-Fi technologies. We are also a leader in video processing and video encoding/decoding technology, with a significant AI research effort that intersects with both wireless and video technologies. Founded in 1972, InterDigital is listed on Nasdaq.

InterDigital is a registered trademark of InterDigital, Inc.

For more information, visit: 

Summary

This internship is part of InterDigital's video coding research activities and focuses on improving the efficiency of the Versatile Video Coding (VVC) standard. The project explores the use of filter bank classification within the in-loop filtering stage of a video codec, with the objective of improving coding efficiency and reconstruction quality.

Video content represents a major portion of today's network traffic, making efficient compression a critical challenge. VVC, the latest international video coding standard developed by ISO/IEC and ITU‑T, introduces several in-loop filtering tools—such as Adaptive Loop Filter (ALF), Bilateral Filter (BIF), Sample Adaptive Offset (SAO), and Cross-Component SAO (CCSAO)—to enhance reconstructed video quality.

The goal of this internship is to investigate a novel filtering approach that combines filter banks with a classification mechanism, potentially driven by machine learning techniques. The intern will study how classification can be used to select or adapt filtering strategies at the in-loop stage, with the aim of improving objective quality metrics (e.g., PSNR) and overall coding performance. The main objectives of the internship are:

• To analyze the state of the art in video in-loop filtering and classification-based approaches

• To investigate machine learning techniques suitable for filter bank classification in video coding

• To design and implement a classification framework for selecting or adapting in-loop filters

• To integrate the proposed classifier into a VVC-based video codec

• To evaluate the impact of the proposed approach on coding efficiency and visual quality

Responsibilities

The intern will be involved in the following tasks:

• Conduct a literature review on machine learning and classification methods applied to image and video processing

• Design a complete machine learning pipeline for filter bank classification, including feature extraction, training, and evaluation

• Implement and train classification models using Python-based tools

• Integrate the trained classifier into a video coding framework (C++ codec environment)

• Analyze experimental results and compare performance against baseline methods

• Document the work and contribute to internal technical reports or publications

Qualifications

Required Qualifications

• Background in machine learning or pattern classification

• Good programming skills in Python

• Strong interest in video coding, signal processing, and image processing

Preferred Skills

• Knowledge of C++ programming

• Familiarity with deep learning frameworks (e.g., PyTorch)

• Experience with scripting, experimentation, or research-oriented code development

Additional Requirements

• Research-oriented mindset

• Basic understanding of digital signal processing and image/video analysis

• Ability to work independently and communicate technical results clearly

Keywords: Video coding, Versatile Video Coding (VVC), in-loop filtering, machine learning, classification, filter banks

Expected Outcomes:

By the end of the internship, the intern is expected to deliver:

• A complete and documented framework for training a classification model for filter bank selection

• An integrated prototype of the classifier within a VVC video codec

• Experimental results demonstrating the impact of classification-based filtering on coding performance

Location: Rennes, France

InterDigital is an equal employment opportunity employer. InterDigital will not engage in or tolerate unlawful discrimination with regard to any employment decision, policy or practice based on a person's sex, gender, pregnancy (including childbirth, breastfeeding and related medical conditions), age, race, color, religion, creed, national origin, ancestry, citizenship, military status, veteran status, mental or physical disability, medical condition, genetic information, sexual orientation, gender identity or expression, or any other factor protected by applicable federal, state or local  law. This policy applies to all terms and conditions of employment, including, but not limited to, recruiting, hiring, compensation, benefits, training, assignments, evaluations, coaching, promotion, discipline, discharge and layoff.