[OPEN][RI-IML_2019-CG-DM-HCI-008] Reconstruction of Personalized 3D Human Body Model

This internship will focus on the 3D reconstruction of the human body. Virtual body enables to generate personalized avatars which are more and more required in VR, AR, gaming and many other virtual applications. It helps increasing the embodiment and preventing from cybersickness. The intern will be included in the Immersive Lab within the Virtual Production group at Technicolor Rennes. Several tools and pieces of software developed by the team are available and will be improved. The work will consist in: (1) study the state of the art around 3D reconstruction of human avatars [1], and in particular evaluate a technique based on RGB-D video [2], (2) improve the existing camera rig and reconstruction algorithm in order to provide at the end a realistic digital double of the people.

[1] J. Achenbach, T. Waltemate, M. Erich Latoschik, and M. Botsch. 2017. Fast generation of realistic virtual humans. In Proceedings of the 23rd ACM-VRST '17
[2] Alldieck, T., Magnor, M. A., Xu, W., Theobalt, C., & Pons-Moll, G. (2018). Video Based Reconstruction of 3D People Models. arXiv preprint arXiv:1803.04758.

Skills  : Computer graphics, Python, Deep Learning, Math (optimization and geometry), English, motivated by research.

Keywords  : Geometry Processing, 3D reconstruction, deep learning

 

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][RI-HOME_2019-CV-DM-HCI-033] Advanced deep learning methods for audio event detection in domestic environment

The internship addresses detection of audio events in domestic environment for emerging real life applications to be implemented within a set-top-box.

This task, which has been benchmarked in DCASE challenges (see [1] for the DCASE 2018), has attracted a lot of attention in the past few years. With the advances in deep neural networks (DNN) and the release of large-scale audio datasets, numerous approaches have been investigated in the literature, including both supervised and weakly-supervised [2] methods. Grounded on DCASE 2019 challenge with benchmarked datasets, the internship targets to build a state-of-the-art DNN model to do the inference accurately. Several settings might be considered: single channel vs. multichannel inputs, supervised vs. weakly supervised learning where the annotations are noisy and/or incomplete. The intern will conduct both research and implemention while investigating the use of advanced DNN architectures and data augmentation strategies for the considered tasks. Depending on the actual work and the obtained result, the work may be concluded by a participation in the DCASE 2019 challenge and by a submission of a scientific publication in an international conference/workshop.

[1] IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE), http://dcase.community/challenge2018/.
[2] Romain Serizel et al., “Large-Scale Weakly Labeled Semi-Supervised Sound Event Detection in Domestic Environments,” Proc. DCASE2018 Workshop, July 2018. https://hal.inria.fr/hal-01850270.

Skills  : Machine learning (deep learning), audio processing, Python.

Keywords  : Machine learning (deep learning), audio signal processing, weakly supervised learning, acoustic event detection.

 

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][RI-IML_2019-HCI-009] Light-efficiency calculation tool for Augmented Reality glasses

Diffractive Augmented Reality glasses are based on multi-layers of waveguides provided with diffractive flat optical components. The combination of several waveguides, multiple colors and angular incident bands on structures diffracting multiple modes makes it difficult to calculate an overall performance of the system in terms of light-efficiency and colorimetry. The goal of the internship is to develop tools with electromagnetic simulation packages (Comsol), matlab and Zemax in order to quantify the color triangle and light-efficiency of this complex system.

Skills  : Understanding of electro-magnetism and diffraction theory. Simulation tools : Comsol, Development skills, Matlab, Zemax.

Keywords  : Nanojet, AR glasses, Diffraction

 

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][RI-IML_2019-CG-HCI-005] Interactive Cage Creation for Facial Mesh Deformation

The purpose of the internship is to design and implement an efficient pipeline to 1/ generate automatically high-quality cages for 3D facial meshes and 2/ deform these meshes in the human face deformation space. The intern will be included in the Immersive Lab within the Virtual Production group at Technicolor Rennes. Several tools and software developed by the team are available and will be used. The work will consist in: (1) study the state of the art around cage generation and facial deformations, (2) design a pipeline to generate the cage based on any 3D facial mesh, (3) propose an approach to constrain the deformations space of the cage (4) if there is time, conduct a user study for publication.

Skills  : Computer graphics, Python, Editing/Animation tool (Blender, Maya), Maths (optimization and geometry), English, motivated by research.

Keywords  : Geometry Processing, Facial Animation, Human Interaction

 

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][RI-ISL_2019-DM-HCI-016] Gesture Recognition by Deep Learning

Action and Gesture recognition have a growing interest in several application domain essentially in human machine interaction like in automotive, games and digital TV user interface. The goal of this internship is to explore and propose a new framework based on Neural Network to achieve a gesture recognition for digital TV application where features are extracted as well in the spatial and temporal domain.

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

 

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][RI-IML_2019-CV-HCI-031] Automatic extraction and encoding of haptic effects

In order to develop new cinematographic and Mixed-Reality (MR) experiences, immersive visual content is being developed at Technicolor. Besides, sensory effects, such as haptic effects, can be added to this media. However, the creation and encoding of this multisensory content are open issues.

The purpose of the internship is to contribute to this topic by designing algorithms to automatically extract haptic information from immersive videos. The effects should be then encoded into a data format in order to be streamed and rendered to the appropriate end-user terminal. Thus a data format will need to be specified and then implemented into an existing streaming platform (inc. developing the necessary encoder, decoder and frame packing). The second part of the internship will focus on the extraction of the camera motion from an omnidirectional video [1]. This data will be used to drive a motion platform. Additionally, more haptic information could be extracted.

[1] Lee, J., Han, B., & Choi, S. (2016). Motion effects synthesis for 4D films. IEEE transactions on visualization and computer graphics, 22(10), 2300-2314. Skills : Computer vision, C++, Maths, English, motivated by research. Keywords: Haptics, video encoding, automatic extraction

Skills  : Computer vision, C++, Maths, English, motivated by research.

Keywords  : Haptics, video encoding, automatic extraction

 

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.