1_lddmm · Wiki · icm-institute / AramisLab / deformetrica · GitLab

learn from shapes.

Skip to main content 1_lddmm The LDDMM framework proposes to compare shapes (meshes or images) using diffeomorphic transformations of the 2D or 3D ambient space between these objects. To use it, we need to be able to parametrize a large family of transformations of the 2D or 3D space as well as to be able to compute distances between the objects. [Bône et al. 2018] provides a concise reference summarizing the theory behind Deformetrica applications. For more details, see [Durrleman et al. 2014]. Parametric family of deformations To generate deformations, deformetrica uses a set of nnn…

saved by

• Sarah Kushner

related reading

• Modular Manifolds - Thinking Machines Labthinkingmachines.ai
• mls.pdfcs.harvard.edu
• Diffusion models from scratchchenyang.co
• Riemannian Metric Matching for Scalable Geometric Modeling of Distributionsarxiv.org
• Neural Manifold Ordinary Differential Equationsarxiv.org
• Step-by-Step Diffusion: An Elementary Tutorialarxiv.org
• GitHub - jasonwebb/morphogenesis-resources: Resources on the topic of digital morphogenesis (creating form with code). Includes links to major articles, code repos, creative projects, books, software, and more.github.com
• Learning the integral of a diffusion model – Sander Dielemansander.ai
• How I Understand Flow Matchingyoutube.com
• Diffusion model - Wikipediaen.wikipedia.org
• An Introduction to Flow Matching and Diffusion Modelsdiffusion.csail.mit.edu
• Normalizing flowsbehindml.com