Adobe was granted a patent for label-free video object segmentation

{
  "signal_id": "11ad3deb-b5f8-5f9a-957f-77116b3e5dba",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-10-30T00:39:04+00:00",
  "company": {
    "name": "Adobe",
    "domain": "adobe.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06T 7/215",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 7/162",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 7/194",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 7/248",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06T 2207/10016",
        "label": "Image data processing or generation, in general"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Software",
      "Enhanced Content"
    ],
    "detail": "In October 2026 Adobe patented a training-free method for separating moving objects from their backgrounds in user-generated and other real-world video.",
    "summary": "Adobe was granted a patent for label-free video object segmentation",
    "event_at": "2026-10-27",
    "inventors": [
      {
        "name": "Silky Singh",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Shirpad Deshmukh",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Rishabh Jain",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/rishabh99jain"
      },
      {
        "name": "Mayur Hemani",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/mayur-hemani"
      },
      {
        "name": "Mausoom Sarkar",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/mausoomsarkar"
      },
      {
        "name": "Balaji Krishnamurthy",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/balaji-krishnamurthy-4241695"
      }
    ],
    "tech_area": "image processing / graphics",
    "event_kind": "grant_date",
    "grant_date": "2026-10-27",
    "source_url": "https://patents.google.com/patent/US12776047",
    "cpc_primary": {
      "code": "G06T 7/215",
      "label": "Image data processing or generation, in general"
    },
    "patent_title": "Video object segmentation using estimated motion information and image features",
    "patent_number": "US12776047",
    "uspto_assignee": "Adobe Inc.",
    "patent_abstract": "Various disclosed embodiments are directed to learning-free video object segmentation (VOS) of one or more video frames. In various instances, such VOS does not rely on human supervision or labeling and can be generalized or applied to any video “in the wild.” This is because training and fine-tuning are not required for VOS. Particular embodiments perform VOS based on feature similarity of different sections of a video frame and/or estimated motion similarity of different sections of the video frame, such as via a graph cut on a graph.",
    "precision_class": "structural",
    "invention_explanation": "The system identifies objects by comparing visual features and how different parts of each video frame move, without requiring labeled examples or additional training.",
    "technologies_mentioned": [
      "video segmentation",
      "computer vision",
      "motion estimation",
      "image processing"
    ]
  }
}

curl https://signals.autobound.ai/v1/signals/11ad3deb-b5f8-5f9a-957f-77116b3e5dba \
  -H "X-API-KEY: $AUTOBOUND_API_KEY"

curl -X POST https://signals.autobound.ai/v1/companies/enrich \
  -H "X-API-KEY: $AUTOBOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain":"adobe.com","limit":20}'