[CLOSED] [ISL_CV_DM_VP_022] Framework for Deep Learning Inference

Deep learning approach enable very efficient signal processing and pattern recognition tasks in several fields including image segmentation or 3D modelling. Many frameworks are available for designing and training deep model. But the deployment of deep based inference solution in professional environments is still difficult because of many integration constraints (eg GPU, interactivity, resource sharing and complexity of DL libraries). The goal of this internship is to develop a library and a workflow for transferring, converting and using deep models into final VFX production environments. A possible use case is the interactive object segmentation

Skills : machine learning, deep learning, computer vision, video/image processing, PyTorch, TensorFlow or Keras deep learning frameworks, Python or C++. Cuda, OpenCL

Keywords : machine learning (deep learning), video processing, computer vision, segmentation

 

This internship is located in Rennes, France. If interested, please apply at stage.technicolor@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

[CLOSED] [ISL_CV_DM_VP_023] Deep Learning for Rotoscoping Task

Due to the massive amount of pictures stored by Facebook, YouTube and other applications, there is a need to efficiently compress similar images to reduce storage capacity requirements. The redundancy of those similar images can be successfully exploited by leveraging current image/video coding schemes.

In this internship we would like to investigate new paradigms using machine learning on patch manifolds to predict or restore image patches. In particular we would like to study those techniques as a pre and/or post-processing added to traditional HEVC/JPEG encoders

The candidate will have to implement and evaluate various methods based on manifolds, machine learning, and minimization problems. He/she will use an existing encoding framework for validation. He/she will work with other people working on similar issues.

Skills : Computer vision and image processing, Machine learning, image/video compression, applied mathematics, C/C++ programming

Keywords : Video compression, Machine Learning

This internship is located in Rennes, France. If interested, please apply at stage.rennes@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

[CLOSED] [ISL_VP_024] Deep Learning-Based Filtering for Future Video Codec

The topic of this internship is the image (or video) compression using deep learning approaches. The candidate will have the opportunity to work on state-of –the art video coding technology and improve some crucial parts of a video codec using CNN based filtering. Optimization of complexity and rate-distortion criteria are also part of the challenge. The candidate should be familiar with current deep learning software packages and have a good background in image processing in general

Skills : deep learning algorithms and software, programming (C++/python), image processing (denoising, deblocking etc.), video compression

Keywords : image restoration, deep learning, video compression

 

This internship is located in Rennes, France. If interested, please apply at stage.technicolor@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

[OPEN] [ISL_VP_025] Exploration of Advanced Video Compression Technologies

Early 2018, MPEG and VCEG (named JVET) are jointly beginning the standardization of a new video compression technology, known as H.266, as a successor to the AVC and HEVC video coding standards. Technicolor is deeply involved in this standardization process by proposing tools improvements as well as new ones. The internship aims at exploring new ways for improving video compression. The tracks mostly relate to improved inter prediction with improved motion representation, prediction and coding. It could be the enhancement of the averaging of the bidirectional prediction based on some intrinsic features of the corresponding image area. The research work will be held in the reference software developed by JVET. The internship will take place in a research team of several video coding and standardization experts. It will also benefit from the Technicolor experts working on HDR and Color science

Skills : video coding, signal and video processing, C++

Keywords : video coding, motion prediction, motion coding, HEVC, JVET

 

This internship is located in Rennes, France. If interested, please apply at stage.technicolor@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

[CLOSED] [ISL_VP_026] Quantization Matrices for Future Video Compression Standard (H266)

Since JPEG, main picture compression standards make use of quantization matrices to modulate the quantization step for each transformed coefficient. The goal of this internship is to study and implement quantization matrices for the next video compression standard, which development is in progress: state of the art, visual evaluation, coding algorithms and implementation

Skills : interested in visual perception and video compression (basic knowledge is expected), ability to compile and review technical publications, C/C++ coding, Matlab, comfortable with embedded software and dedicated hardware context, autonomy and scientific rigor

Keywords : HEVC, h266, video compression, quantization, visual perception

 

This internship is located in Rennes, France. If interested, please apply at stage.technicolor@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

[CLOSED] [ISL_VP_034] 360 Degree Camera Color Alignment

360° camera rigs employ multiple cameras for capturing a full spherical scene. However, small variations between the camera optics, sensors and responses may cause color, contrast and luminance variations between each part of the scene. This can pause significant challenges both to stitching algorithms as well as to subsequent color correction applied to the stitched 360° content. The goal of this project is to analyze content from 360° cameras (both from a pre-existing dataset and captured during the project) to quantify the variations present between different views. Then, efficient solutions will be developed and tested for correcting such variations, ensuring that the images from different cameras within a 360° rig are colorimetrically aligned

Skills : matlab or python; Image processing/analysis; Some understanding of color science desirable

Keywords : Virtual reality, 360°, camera calibration, color correction

 

This internship is located in Rennes, France. If interested, please apply at stage.technicolor@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

[CLOSED] [ISL_CV_VP_035] Color Constancy by Deep Learning

Color Constancy aims to estimate the color of light source in the image. Many image processing tasks such as scene understanding may benefit from Color Constancy by using the corrected object colors. The goal of this internship is to explore and propose a new framework based on convolutional neural network (CNNs) to achieve the illuminant estimation for color constancy processing. Comparison with traditional methods should be conducted through a user test

Skills : Matlab/Python/C programming, ideally with image processing expertise Ability to write well-structure and documented code Good written and spoken English Excellent team working skills as the internship forms a part of a larger project, involving many team members Ability to work independently

Keywords : Machine Learning, Deep Learning, SVM, Clustering, Color Constancy

 

This internship is located in Rennes, France. If interested, please apply at stage.technicolor@technicolor.com by sending us your resume and a cover letter with the internship reference in the email subject line.

By continuing to browse this site, you agree to the use of cookies. When placed on your device, cookies enable site visit statistics to be collected and services to be better adapted to your needs, such as language preferences. For more information and to configure cookies, click here.