I am a Research Scientist in the AR Perception group at Google.
My research interests lie at the intersection of machine learning, computer vision, and human-computer interaction, with a primary focus on the perception and synthesis of human activities, aiming to digitize humans in various aspects. Technically, I am interested in deriving new machine learning algorithms, particularly generative temporal models to capture human dynamics and generate human-like interactions.
Prior to joining Google, I was a PhD student in the Advanced Interactive Technologies lab at ETH Zurich, advised by Prof. Dr. Otmar Hilliges. The focus of my thesis was deep generative temporal modeling with applications in the tasks of 3D motion modeling and prediction, building 3D face avatars, and modeling and synthesis of free-form human actions such as digital representations of drawings and handwritten text.
E-mail : aksan (at) google (dot) com. Feel free to reach out to me for questions or potential collaborations.
|Dec 2022||A new chapter: I started working at Google Zurich.|
|Nov 2022||My thesis is awarded with the Fritz Kutter award.|
|Aug 2022||Done! I succesfully defended my PhD thesis.|
- LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent SpaceProceedings of the European Conference on Computer Vision (ECCV) 2022
- D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object InteractionsProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
- A Spatio-temporal Transformer for 3D Human Motion PredictionInternational Conference on 3D Vision (3DV) 2021
- CoSE: Compositional Stroke EmbeddingsAdvances in Neural Information Processing Systems (NeurIPS) 2020