Hinge Health was granted a patent for multi-object pose estimation.

{
  "signal_id": "395f7ae9-4407-5d08-9286-2d2bf8ff4c25",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-15T19:50:57+00:00",
  "company": {
    "name": "Hinge Health",
    "domain": "hingehealth.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06T 7/74",
        "label": "Image data processing or generation, in general"
      },
      {
        "code": "G06V 10/82",
        "label": "Image or video recognition or understanding"
      },
      {
        "code": "G06V 20/41",
        "label": "Image or video recognition or understanding"
      },
      {
        "code": "G06V 40/10",
        "label": "Image or video recognition or understanding"
      },
      {
        "code": "G06T 2207/10016",
        "label": "Image data processing or generation, in general"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Machine Learning",
      "Healthcare Technology"
    ],
    "detail": "In August 2026 Hinge Health patented computer-vision technology for analyzing movement in digital physical-therapy and remote-care applications.",
    "summary": "Hinge Health was granted a patent for multi-object pose estimation.",
    "event_at": "2026-08-25",
    "inventors": [
      {
        "name": "Bharathkumar Ramachandra",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Paul Anthony Kruszewski",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "image processing / graphics",
    "event_kind": "grant_date",
    "grant_date": "2026-08-25",
    "source_url": "https://patents.google.com/patent/US12718405",
    "cpc_primary": {
      "code": "G06T 7/74",
      "label": "Image data processing or generation, in general"
    },
    "patent_title": "Pose parsers",
    "patent_number": "US12718405",
    "uspto_assignee": "Hinge Health, Inc.",
    "patent_abstract": "An apparatus is provided an apparatus to estimate poses of multiple objects from a two-dimensional image. The apparatus includes a communications interface to receive raw data from an external source. The raw data includes a representation of a first object and a second object. In addition, the apparatus includes a memory storage unit to store the raw data. The apparatus also includes a first neural network engine to detect parts of the first object and the second object and to generate an intermediate representation of the parts. Furthermore, the apparatus includes a second neural network engine to apply a transformer neural network to the intermediate representation to parse the parts into first object parts and second object parts to generate a first pose of the first object from the first object parts and to generate a second pose of the second object from the second object parts.",
    "precision_class": "structural",
    "invention_explanation": "A neural-network system that examines a 2D image, identifies parts of multiple objects, and estimates their positions and orientations.",
    "technologies_mentioned": [
      "computer vision",
      "neural networks",
      "pose estimation",
      "image processing"
    ]
  }
}

curl https://signals.autobound.ai/v1/signals/395f7ae9-4407-5d08-9286-2d2bf8ff4c25 \
  -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":"hingehealth.com","limit":20}'