{
  "patent_number": "US 12282696",
  "country": "US",
  "title": "How AI Transfers Visual Styles Between Images While Keeping Structure",
  "original_title": "Method and system for semantic appearance transfer using splicing ViT features",
  "summary": "This patent describes an AI method to generate a new image that combines the structure of one input image with the visual style of another, semantically related image, using a pre-trained Vision Transformer model.",
  "what_it_does": "This method generates a new image by taking two inputs: a 'source structure image' and a 'target appearance image'. The goal is to create a 'third image' that keeps the original structure from the first image but adopts the visual look from the second. For example, if you provide a picture of a person (source structure) and a picture of a famous painting (target appearance), the system aims to redraw the person in the style of the painting. It achieves this by training a 'generator' (an Artificial Neural Network, or ANN) to minimize differences between the appearance of the generated image and the target appearance, and optionally, to minimize differences between the structure of the generated image and the source structure (Claim 1, Claim 3). A key component is using a pre-trained, fixed Vision Transformer (ViT) model as a 'semantic prior' to understand and correctly match objects between the two input images (Abstract, Claim 8). This allows the generator to be trained effectively with just a single pair of input images.",
  "what_it_does_not_cover": [
    "Does not cover style transfer methods that do not use a Vision Transformer (ViT) model as a semantic prior for training the generator.",
    "Does not cover image generation where the structure is also created or significantly altered, as it focuses on preserving the 'first structure' (Claim 1).",
    "Does not cover methods that require large datasets for training the generator itself, as this patent emphasizes training with only a 'single structure/appearance image pair' (Abstract).",
    "Does not cover transferring appearance without semantic awareness, meaning it aims to 'paint' semantically related objects, not just apply a general filter.",
    "Does not cover methods that rely solely on adversarial training, as the patent specifies training 'without adversarial training' (Abstract)."
  ],
  "filed": "2022-12-18",
  "granted": "2025-04-22",
  "expires": "2042-12-18",
  "status": "active",
  "holder": "Yeda Research and Development Co",
  "holder_url": "https://patentbrief.org/company/yeda-research-and-development-co",
  "inventors": [
    {
      "name": "Narek TUMANYAN",
      "url": "https://patentbrief.org/inventor/narek-tumanyan"
    },
    {
      "name": "Tali Dekel",
      "url": "https://patentbrief.org/inventor/tali-dekel"
    },
    {
      "name": "Shai Bagon",
      "url": "https://patentbrief.org/inventor/shai-bagon"
    },
    {
      "name": "Omer BAR TAL",
      "url": "https://patentbrief.org/inventor/omer-bar-tal"
    }
  ],
  "times_cited": 2,
  "tags": [
    "ai_ml",
    "software",
    "consumer_electronics",
    "telecommunications",
    "gaming"
  ],
  "abstract": "Using a pre-trained and fixed Vision Transformer (ViT) model as an external semantic prior, a generator is trained given only a single structure/appearance image pair as input. Given two input images, a source structure image and a target appearance image, a new image is generated by the generator in which the structure of the source image is preserved, while the visual appearance of the target image is transferred in a semantically aware manner, so that objects in the structure image are “painted” with the visual appearance of semantically related objects in the appearance image. A self-supervised, pre-trained ViT model, such as a DINO-VIT model, is leveraged as an external semantic prior, allowing for training of the generator only on a single input image pair, without any additional information (e.g., segmentation/correspondences), and without adversarial training. The method may generate high quality results in high resolution (e.g., HD).",
  "url": "https://patentbrief.org/patent/us/12282696/method-and-system-for-semantic-appearance-transfer-using-splicing-vit-features",
  "markdown_url": "https://patentbrief.org/patent/us/12282696/method-and-system-for-semantic-appearance-transfer-using-splicing-vit-features/md",
  "google_patents_url": "https://patents.google.com/patent/US12282696",
  "relatedPatents": [
    {
      "patentNumber": "12141700",
      "countryCode": "US",
      "title": "How AI Generates Images Based on Style and Content Cues",
      "url": "https://patentbrief.org/patent/us/12141700/generative-adversarial-network-for-generating-images"
    },
    {
      "patentNumber": "20230162023",
      "countryCode": "US",
      "title": "Automated AI for Adapting to New Data Without Retraining",
      "url": "https://patentbrief.org/patent/us/20230162023/system-and-method-for-automated-transfer-learning-with-domain-disentanglement"
    },
    {
      "patentNumber": "12039012",
      "countryCode": "US",
      "title": "Sharing AI Knowledge Between Private Datasets Using Synthetic Data",
      "url": "https://patentbrief.org/patent/us/12039012/systems-and-methods-for-heterogeneous-federated-transfer-learning"
    },
    {
      "patentNumber": "11062228",
      "countryCode": "US",
      "title": "How AI Learns New Tasks Using Old Data Labels",
      "url": "https://patentbrief.org/patent/us/11062228/gpt-3-few-shot-learning"
    },
    {
      "patentNumber": "10452978",
      "countryCode": "US",
      "title": "How AI Models Understand Language Using 'Attention'",
      "url": "https://patentbrief.org/patent/us/10452978/transformer-attention-mechanism"
    }
  ]
}