{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-11954899","patent":{"patent_number":"US-11954899","title":"Systems and methods for training models to predict dense correspondences in images using geodesic distances","assignee":null,"inventors":[],"filing_date":"2021-03-11T00:00:00.000Z","publication_date":"2024-04-09T00:00:00.000Z","cpc_codes":["G06T","G06V","G06F","G06F","G06F","G06N","G06T","G06T","G06V","G06V","G06V","G06V","G06T","G06T","G06T","G06T"],"num_claims":20,"abstract":"Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer models of a subject. In addition, one or more geodesic distances derived from the surfaces of one or more of the 3D models may be used to generate one or more loss values, which may in turn be used in modifying the model's parameters during training."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Systems and methods for training models to predict dense correspondences in images using geodesic distances","description":"Systems and methods for training models to predict dense correspondences across images such as human images. A model may be trained using synthetic training data created from one or more 3D computer m","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-11954899","license":"CC-BY-4.0-like","license_terms":"AI-generated analysis on this page (summary, layman_explanation, technical_analysis, business_analysis, faqs) may be reused with attribution and a visible link back to the canonical URL above. Patent abstracts, claims, and bibliographic data are USPTO public domain.","required_link":"https://patentable.app/patents/US-11954899","citation_suggestion":"Patentable. \"Systems and methods for training models to predict dense correspondences in images using geodesic distances\" (US-11954899). https://patentable.app/patents/US-11954899","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-11954899","json":"https://patentable.app/api/llm-context/US-11954899","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T14:46:49.471Z"}