Presenting morphology prediction at IMC21
I presented our single-image 3D morphology prediction work at IMC21, the 21st International Microscopy Congress, held at ACC Liverpool from 31 August to 4 September. The method tackles the inverse problem of electron microscopy: given one STEM image of a supported nanoparticle, recover the 3D atomic structure that produced it. We use an image-conditioned point…
Keep reading
CIMP accepted at the AI4Physics workshop, ICML 2026
Our paper Contrastive Image-Metadata Pre-Training for Materials Transmission Electron Microscopy has been accepted at the AI4Physics workshop at ICML 2026 in Seoul. In it we release the first paired HAADF-STEM image and metadata dataset, 7,330 micrographs annotated with their acquisition parameters, and use it to train a CLIP-style encoder that links an image to the…
Keep reading
🚨New paper 🚨: 3D nanoparticle morphology prediction from single STEM images
The last paper from my PhD has just been published in npj Computational Materials! In this article we try to solve the inverse problem of going from STEM image back to the 3D atomic structure that gave rise to it. We employ an image-conditioned point cloud diffusion model for this purpose and achieve pretty good…
Keep readingSomething went wrong. Please refresh the page and/or try again.
