Speaker: Michael Fischer, Research Scientist at Adobe Research (https://mfischer-ucl.github.io/)
Where & when: Tuesday June 30th @ 11:00, Seminario DIIS Manuel Silva, Edif. Ada Byron
Bio: Michael Fischer is a research scientist at Adobe research London. He obtained his PhD from University College London (UCL), advised by Niloy Mitra and Tobias Ritschel. Michael has authored several top-tier publications (CVPR, ICCV, SIGGRAPH, ...) and is a recipient of both the Meta PhD scholarship and the Rabin Ezra scholarship as well as the Eurographics PhD Thesis Award. His research interests focus on image- and scene-understanding, material perception, selection and editing and efficient optimization.
Talk abstract: In this talk, we'll explore image understanding from a material-centric perspective, namely through the lens of material appearance. Materials distinguish themselves by their response to light, which is governed and modelled through physical properties like roughness or gloss - however, understanding such properties is a non-trivial task for current machine learning models and network architectures. We'll see how we can select materials similar to a given query material, significantly improve selection fidelity along several axes and eventually venture beyond 2D, to enable selection in the 3D domain.
