Description du sujet de thèse

Three-dimensional (3D) models, representing a person, animal, or mechanical object, are commonly used in various applications such as digital entertainment, virtual reality, and computer-aided design. Robust 3D watermarking is a promising technique for copyright protection of 3D models (mainly represented as 3D meshes). The inserted watermark should be invisible and robust to different processing operations on the watermarked 3D models. In the proposed thesis project, we aim to develop new and reliable methods for watermarking 3D models by leveraging the deep learning approach. A specially designed deep neural network is trained in an end-to-end manner to perform robust watermark insertion and extraction for 3D models. This replaces the manual design of watermarking features and functions, which is often laborious and generally suboptimal.
- First, we begin with a literature review that consists of a detailed reading and analysis of important and recent 3D mesh watermarking methods, as well as representative research in related fields such as deep-learning-based image watermarking and 3D shape analysis.
- Second, we would like to implement a specifically designed neural network to achieve robustness against the difficult connectivity attacks (which can radically change the number and position of mesh vertices while preserving the 3D shape).
- Third, in order to better adapt to usage scenarios of 3D models (e.g., also protecting the photometric content of models and being able to extract watermarks from 2D views of 3D models), we will conduct original studies on the interaction between different types of mesh information for watermark insertion and extraction.
- Qualified candidates should have a Master/Engineer degree in Computer Science or related fields.
- Experience in 3D model processing and/or machine learning will be a plus.
- Proficiency in Python programming.
- Excellent communication skills and strong motivation.

Contexte de travail

The Gipsa-lab is a joint research laboratory of the CNRS, Grenoble-INP -UGA and the University of Grenoble Alpes. It is under agreement with Inria and the Observatory of Sciences of the Universe of Grenoble. He conducts theoretical and applied research on AUTOMATICS, SIGNAL, IMAGES, SPEECH, COGNITION, ROBOTICS and LEARNING.
Multidisciplinary and at the interface between the human, the physical and digital worlds, our research is confronted with measurements, data, observations from physical, physiological and cognitive systems. They focus on the design of methodologies and algorithms for processing and extracting information, decisions, actions and communications that are viable, efficient and compatible with physical and human reality. Our work is based on mathematical and computer theories for the development of models and algorithms, validated by hardware and software implementations.
By relying on its platforms and partnerships, Gipsa-lab maintains a constant link with applications in a wide variety of fields: health, environment, energy, geophysics, embedded systems, mechatronics, processes and industrial systems, telecommunications, networks, transport and vehicles, operational safety and security, human-computer interaction, linguistic engineering, physiology and biomechanics, etc.
Due to the nature of its research, Gipsa-lab is in direct and constant contact with the economic environment and society.
Its potential as teacher-researchers and researchers is invested in training at the level of universities and engineering schools on the Grenoble site (Grenoble Alpes University).
Gipsa-lab develops its research through 16 teams or themes organized into 4 divisions:
• Automatic and Diagnosis (PAD)
• Data Science (PSD)
• Speech and Cognition (PPC)
• Geometries, Learning, Information and Algorithms (GAIA).
The staff supporting research (38 engineers and technicians) is distributed in the common services distributed within 2 divisions:
• The Administrative and Financial Pole
• The Technical Pole
Gipsa-lab has around 150 permanent staff, including 70 teacher-researchers and 41 researchers. It also welcomes guest researchers and post-docs.
Gipsa-lab supervises nearly 150 theses, including around 50 new ones each year. All the theses carried out in the laboratory are financed and supervised by teacher-researchers and researchers, including 50 holders of an HDR.
Finally, around sixty Master's trainees come each spring to swell the ranks of the laboratory.
The proposed PhD thesis work will be conducted in the ACTIV (Learning Classification Image and Video Processing) team of GIPSA-lab (Grenoble), with collaboration with the LIRIS laboratory in Lyon. The PhD student will be jointly advised by Dr. Kai Wang (thesis director, GIPSA-lab) and Prof. Florent Dupont (LIRIS). Working language can be either French or English.

Le poste se situe dans un secteur relevant de la protection du potentiel scientifique et technique (PPST), et nécessite donc, conformément à la réglementation, que votre arrivée soit autorisée par l'autorité compétente du MESR.

Contraintes et risques

No

Informations complémentaires

Beginners accepted