{"schema_version":"1.0","canonical_url":"https://patentable.app/patents/US-12008710","patent":{"patent_number":"US-12008710","title":"Generating light-source-specific parameters for digital images using a neural network","assignee":null,"inventors":[],"filing_date":"2022-12-06T00:00:00.000Z","publication_date":"2024-06-11T00:00:00.000Z","cpc_codes":["G06T","G06N","G06N","G06N","G06T","G06T","G06T","G06T","G06T","G06T","G06T","G06T","G06T","G06T"],"num_claims":20,"abstract":"This disclosure relates to methods, non-transitory computer readable media, and systems that can render a virtual object in a digital image by using a source-specific-lighting-estimation-neural network to generate three-dimensional (“3D”) lighting parameters specific to a light source illuminating the digital image. To generate such source-specific-lighting parameters, for instance, the disclosed systems utilize a compact source-specific-lighting-estimation-neural network comprising both common network layers and network layers specific to different lighting parameters. In some embodiments, the disclosed systems further train such a source-specific-lighting-estimation-neural network to accurately estimate spatially varying lighting in a digital image based on comparisons of predicted environment maps from a differentiable-projection layer with ground-truth-environment maps."},"analysis":{"summary":null,"layman_explanation":null,"technical_analysis":null,"business_analysis":null,"faqs":null,"topics":[],"tech_cluster":null},"seo":{"title":"Generating light-source-specific parameters for digital images using a neural network","description":"This disclosure relates to methods, non-transitory computer readable media, and systems that can render a virtual object in a digital image by using a source-specific-lighting-estimation-neural networ","keywords":[]},"attribution":{"source":"Patentable","source_url":"https://patentable.app","canonical_url":"https://patentable.app/patents/US-12008710","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-12008710","citation_suggestion":"Patentable. \"Generating light-source-specific parameters for digital images using a neural network\" (US-12008710). https://patentable.app/patents/US-12008710","copyright_holder":"Nomic Interactive Technology LLC"},"links":{"html":"https://patentable.app/patents/US-12008710","json":"https://patentable.app/api/llm-context/US-12008710","site":"https://patentable.app","llms_txt":"https://patentable.app/llms.txt"},"generated_at":"2026-05-31T14:43:04.596Z"}