[CLOSED] [MCL_2016_CV_CG_HCI_VP_008] Dynamic and virtual media screen in domestic environment 

The goal of the internship is to develop an Augmented Reality application for mobile device (typically a tablet), which allows a user to easily define and activate a virtual media screen attached to a wall of his choice, with personalized size, inside its house.

The internship will focus on natural image features detection & tracking in that particular context, using related computer vision libraries. The development will be typically done on Android or Windows tablet using related SDK and additional libraries that may help for the internship’s purpose.

Specific knowledge in computer vision, good programming skills in C++ , Android or Windows, possibly CUDA/OpenCL, 3D rendering library (Unity 3D, Unreal Engine)

KeywordsComputer vision, video processing, image feature detection, pose camera tracking, real-time processing.

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_2016_VP_009] Authored Lighting Control

The recent introduction of internet connected light sources brings the possibility to augment the viewing experience of watching movies by driving the room’s illumination in sync with the movie content. The purpose of the internship is to develop a system that allows authoring of room illumination in a controlled environment (a grading studio). Second, as the lighting environment in consumers’ homes will not match that found in a grading studio, an algorithm for mapping illumination from one environment into another will be developed. The resulting system will be able to enhance a movie by incorporating the room illumination into the story-telling.

Skills: : Algorithm design, C/C++ programming skills, A creative mindset.

Keywords: Internet connected illumination, Color grading, Illumination reproduction

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] [DPL_2016_SP_VP_011] Signal Processing for Anti-piracy

Piracy has been significantly facilitated by the commercial deployment of software to manipulate digital multimedia content, and the development of rapid and efficient distribution networks. Content protection is mainly ensured by cryptography during the distribution but such protection collapses at rendering time. At that point, complementary forensics solutions are needed to deter piracy. Traitor tracing digital watermarks can be used to pinpoint the source of a leak when it occurs and passive forensics techniques can be employed to characterize pirate samples. The objective of this internship is to enrich Technicolor’s forensics toolbox. Depending on the profile and interest of the candidate, the internship will focus either on improving Content ArmorTM Video Watermarking system, or on designing passive forensics tools to help watermark detection.

Contact us to get more detailed proposals.

Skills: video processing (required), video coding, modeling, inverse problems, perceptual evaluation

Keywords: movie piracy, camcording, watermarking

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_2016_VP_018] Analysis and improvement of the SAO post-filter in HEVC

The new video compression standard H.265/HEVC integrates a Sample Adaptive Offset (SAO) post-processing filter, which significantly improves its performance.

This internship aims first at analysing the performance of the SAO filter depending on the different configurations, considered bit-rates, and video sequence types. After having analysed the strengths and weaknesses of the SAO, the intern will exploit them to propose and implement possible improvements.

Skills : video compression, image processing, C/C++ programming

Keywords : image processing, video coding.

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_2016_CV_VP_019] Light Field Fourier slice re-focusing

Light Fields are defined as all the light rays at every point in space travelling in every direction. It is essentially 4D data (position + direction). Light Fields can be captured either with plenoptic cameras or an array of cameras. Light Fields are gaining a lot of popularity in the field of computational photography because of the additional information they have compared to traditional (2D) imaging. Indeed, Light Fields allow novel post-processing capabilities such as refocusing.

The goal of this internship is to investigate the 4D Fourier spectrum of Light Fields and to implement re-focusing algorithms based on the extraction of 2D slices from the 4D Fourier domain.

Skills: Major in signal/image processing or computer vision. Skills in C++ programming or Matlab.

Keywords : Light Fields, image processing, Fourier transform, spectral analysis

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_2016_CV_VP_020] Perceptual coding for new gen video codec

New generation video codecs, such as H.265/HEVC or VP9, achieve high compression performances w.r.t. the PSNR metric. Perceptual approaches enable to improve even further those performances, while relying on quality metrics that consider the human visual system properties. This internship aims at optimising the use of such metrics within a compression framework.

Skills : video compression, image processing, machine learning, C/C++ programming

Keywords : new-gen video compression.

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_2016_CV_VP_021] Hi Mom! Video chat-specific video compression algorithms

Current commercial video-chat solutions do not take advantage of signal redundancies intrinsic to the application. Despite the fact that these systems operate in closed-world situations, they use standard codecs that, given the bandwidth constrained nature of the task, result in dropped frames, blocking artifacts and a poor user experience. Yet the closed-world nature of video-chat systems means that the codec at both ends of the communication link does not need to adhere to standardized options optimized for generic video content.

In this internship, the aim is hence to exploit the high redundancy that video-chat signals benefit from in developing a codec optimized for the application. The tools envisioned to carry out this include machine learning, overcomplete transforms, sparse coding, online optimization methods and information theory.

Keywords: Video compression, sparse coding, machine learning, face processing

A good candidate will hence need to have confidence with mathematics and implementing mathematical algorithms using languages such as Python, Matlab, or C/C++. Furthermore, we envision putting together a functional demonstration model, and hence a plus would include having some notion of interface development and web sockets, preferably using Python

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_2016_VP_022] Content-dependent Stylization

The color style of a movie or the rendering style of an animation play an important role in conveying the intent of the director, setting the mood and helping the viewer feel more immersed in the content. Creative professionals intuitively know how to use the available tools to that effect. How can non-expert users however effectively select the style that best fits their content?

In this project, we will explore different color and rendering styles. By analyzing different content, we will attempt to establish a link between different styles and content types. This can in turn be used to provide a recommendation system for amateur users or it can drive automatic stylization solutions, e.g. in the context of mobile image and video editing.

Key Skills:

  • Matlab/C/C++ programming
  • Image processing
  • Rendering
  • Excellent English written and spoken skills
  • Ability to communicate research findings and questions

Keywords: stylization, rendering, content analysis, color

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.

[OPEN] [ISL_2016_VP_023] Portrait Declipping using Facial Model

When taking photographs of people under directional light, often parts of the face may be under shadow or over-exposed. Although some detail may be recovered in shadow areas, information in over-exposed areas is completely lost. The recovery of such areas is known as declipping, and although several solutions exist for general cases of over-exposure, special care is necessary when correcting portrait photographs to not alter the appearance of the subject.

The goal of this internship is to design and develop an over-exposure correction method specifically for facial images. The method will make use of existing 3d facial models and potentially explore the possibility of drawing information from other photographs of the same person to accurately reconstruct lost detail in the portrait.

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 : HDR, declipping, face detection, face recognition, inverse tonemapping, ITMO, image processing.

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_2016_CV_VP_028] Multimodal-based Interestingness Prediction

Knowing whether a media content, i.e., image or video, is interesting for a viewer has numerous applications from assets management, improved education, to targeted advertising.

This internship proposal targets the development and implementation of such an interestingness prediction algorithm based on machine learning techniques. One expected output is to submit a system to the 2016 MediaEval (http://www.mutimediaeval.org) task on interestingness.

Skills: machine learning, computer vision, image processing, C++, Python, OpenCV. Audio processing skill would be a plus.

Keywords: multimodal processing, machine learning (deep learning), image video interestingness

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_2016_CV_VP_037] Deep visual search

Supervised and unsupervised learning with deep networks has recently come back into light with impressive performance boosts with regard to state-of-art in difficult problems of signal and image analysis, such as automatic speech recognition, face recognition or large scale visual object categorization. Beside recognition and classification, there are other fundamental tasks that should also benefit from deep learning. In this internship we shall investigate in particular the problem of large scale similarity search, at the heart of audio and visual retrieval. State-of-art techniques rely on compact representations obtained either by various forms of vector quantization or by sparse coding with learned dictionaries. Alternative representations provided by (un)supervised deep learning will be investigated, with experiments led in large scale visual search.

Keywords: Deep learning, distributed signal representation, approximate nearest neighbors, visual search

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_2016_VP_038] Vocal Double

The ability to capture and reproduce the voice timber and the speech prosody of a given person has made impressive progress, e.g., with recent Ircam projects: based on several hours of recording of an actor reading texts, entirely new synthetic speech of incredible resemblance can be uttered in the same language; also, using much less training data, voice timber can also be transferred to some extent to the natural speech of another speaker. In this work, we would like to investigate ways to push further such systems to create polyglot voice doubles, with various applications. The intern will have to get acquainted with existing voice analysis and reproduction (either by synthesis or by transfer) techniques and will try and alleviate the current mono-lingual limitations.

Keywords: Voice analysis, Speech Synthesis, voice conversion

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_2016_CV_VP_039] Multi-image editing

Motivated by exponentially growing collections of personal photos that are stored and shared on-line, recent works investigate various ways of enhancing photos collectively. The rationale is two-fold: related pictures (eg from the same event) should be enhanced in a consistent way; low quality pictures should benefit at most from the content of related high quality ones. The goal of this internship is to devise and experiment novel ways to perform such a multi-enhancement, with a specific focus on the problem of color consistency across different views of the same scene.

Keywords: image enhancement, color homogenization, multi-image manipulation

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] [MCL_2016_CG_CV_VP_048] Real-time 3D surface reconstruction and tracking

The objective is to develop a real-time application that can build a 3D scene model from data captured by a sensor moving around the scene.

The main components are depth measurement, pose estimation and incremental reconstruction

The internship will consist of an analysis of the state of the art, the specification of a solution suited to our needs, and the implementation, testing and improvement of a method.

Skills : Specific knowledge in computer vision, good programming skills in C/C++ , Windows, possibly OpenGL ES/ CUDA.

Keywords : Computer vision, 3D scene analysis, video processing, 3D reconstruction, pose estimation, real-time processing.

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.

[OPEN] [ISL_2016_VP_053] Codec complexity and control bit rate analysis for HEVC

High efficiency video coding (HEVC) is the latest video compression standard released by JCT-VC which aims to achieve 50% compression efficiency over H.264/AVC for similar visual quality metric. HEVC aims to achieve the high compression performance, especially for higher resolution video (beyond HD), through new concepts such as quad-tree block partitioning, greater number of intra-prediction modes, bigger transform sizes, advanced motion vector prediction, better context modelling for CABAC, tiles, wave-front parallel processing, etc. Though the compression efficiency is higher than the H.264/AVC, the complexity of the encoding and decoding algorithms are higher due to the introduction of the above advanced features. Furthermore, the amount of control bits (the bits required for signalling the coding modes, quad-tree splitting, PU partition, etc.) can be higher due to the presence of higher number of prediction modes, quad-tree splitting, etc. This proposal aims to analyse the control logic complexity of HEVC encoder and decoder from the perspective of hardware implementation, and to analyse the intraframe / interframe redundancy in control bits with a view to compressing them further. The results of this study may help in simplifying the control logic and in compressing the control bits in future video compression standards.

Skills : c/c++ programming skills and experience with Visual Studio under windows/ gcc under linux, image processing/video coding algorithms, familiarity with video compression standards such as H.264/AVC or HEVC is a plus, a liking towards programming and code analysis is desired

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.