IC Colloquium: Data-driven image generation now and in the future
Event details
| Date | 11.11.2019 |
| Hour | 16:15 › 17:30 |
| Location | |
| Category | Conferences - Seminars |
By: Jaakko Lethinen - Aalto University
Video of his talk
Abstract:
Data-driven generative image models, particularly Generative Adversarial Networks (GAN), have experienced dramatic advances in the last two years. In this talk, I will present the work that led to the Progressive GAN, the first high-quality megapixel-resolution generative image model, illustrate the difficulties and solutions encountered along the way, and attempt to shed light onto the models’ internal workings. I will conclude with views on current GAN models’ greatest limitations, as well as potential ways of addressing them.
Bio:
Jaakko Lehtinen is a tenured associate professor at Aalto University, and a principal research scientist at NVIDIA Research. He works on computer graphics, computer vision, and machine learning, with particular interests in generative modelling, realistic image synthesis, and appearance acquisition and reproduction. Overall, Jaakko is fascinated by the combination of machine learning techniques with physical simulators in the search for robust, interpretable AI.
Before taking his current positions, Jaakko spent 2007-10 as a postdoc with Frédo Durand at MIT. Prior to his research career he worked for the game developer Remedy Entertainment in 1996-2005 as a graphics programmer, and contributed significantly to the graphics technology behind the worldwide blockbuster hit games Max Payne (2001), Max Payne 2 (2003), and Alan Wake (2009). Since then, his work on facial performance capture has been used extensively by Remedy in the production of the critically-acclaimed Control (2019).
More information
Video of his talk
Abstract:
Data-driven generative image models, particularly Generative Adversarial Networks (GAN), have experienced dramatic advances in the last two years. In this talk, I will present the work that led to the Progressive GAN, the first high-quality megapixel-resolution generative image model, illustrate the difficulties and solutions encountered along the way, and attempt to shed light onto the models’ internal workings. I will conclude with views on current GAN models’ greatest limitations, as well as potential ways of addressing them.
Bio:
Jaakko Lehtinen is a tenured associate professor at Aalto University, and a principal research scientist at NVIDIA Research. He works on computer graphics, computer vision, and machine learning, with particular interests in generative modelling, realistic image synthesis, and appearance acquisition and reproduction. Overall, Jaakko is fascinated by the combination of machine learning techniques with physical simulators in the search for robust, interpretable AI.
Before taking his current positions, Jaakko spent 2007-10 as a postdoc with Frédo Durand at MIT. Prior to his research career he worked for the game developer Remedy Entertainment in 1996-2005 as a graphics programmer, and contributed significantly to the graphics technology behind the worldwide blockbuster hit games Max Payne (2001), Max Payne 2 (2003), and Alan Wake (2009). Since then, his work on facial performance capture has been used extensively by Remedy in the production of the critically-acclaimed Control (2019).
More information
Practical information
- General public
- Free
- This event is internal
Contact
- Host: Wenzel Jakob