My research interests are in machine learning/ artificial intelligence, computer graphics, and vision. I worked as a research scientist at Disney Research, and a senior research associate at ETH Zürich before joining Cambridge and Google. I obtained my M.S. and Ph.D. degrees in Computer Science from ETH Zürich (jointly funded by the Swiss National Science Foundation) and completed a double major degree in Computer Engineering and Electronics Engineering at Koc University (summa cum laude, valedictorian). I have been honored with several awards including the Eurographics Best Ph.D. Thesis Award and the UKRI Future Leaders Fellowship.
Selected publications
-
M3ashy: Multi-modal material synthesis via hyperdiffusion
-
Multigranular evaluation for brain visual decoding
-
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
-
Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity
-
Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
-
Multispectral fine-grained classification of blackgrass in wheat and barley crops
-
SYM3D: Canonicalizing Triplanes via Symmetry for Single-View 3D Learning
-
Exploring the visual feature space for multimodal neural decoding
-
Best Foot Forward: Robust Foot Reconstruction in-the-wild
-
Arf-plus: Controlling perceptual factors in artistic radiance fields for 3d scene stylization
-
αsurf: Implicit surface reconstruction for semi-transparent and thin objects with decoupled geometry and opacity
-
Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
-
Gaussian head & shoulders: High fidelity neural upper body avatars with anchor gaussian guided texture warping
-
Twist and Compute: The Cost of Pose in 3D Generative Diffusion
-
Demystifying noise: Role of randomness in generative AI: Demystifying randomness in generative AI
-
Chord: Generation of collision-free, house-scale, and organized digital twins for 3d indoor scenes with controllable floor plans and optimal layouts
-
Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction
-
Demystifying noise: The role of randomness in generative AI
-
PSHead: 3D Head Reconstruction from a Single Image with Diffusion Prior and Self‐Enhancement
-
FreNBRDF: A Frequency-Rectified Neural Material Representation