{
  "$type": "site.standard.document",
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreiblx3qmduzjns4ebfxtye4r3dri3o3ip5xofmdvk7shuxym6irt4q"
    },
    "mimeType": "image/png",
    "size": 124441
  },
  "description": "A processor includes a sampling unit configured to hierarchically sample a 2D image collected through any image collection device and pose information of the image collection device corresponding to the 2D image, and a rendering unit configured to perform SLAM through real-time rendering for data…",
  "path": "/patents/1385533",
  "publishedAt": "2026-06-04T00:00:00.000Z",
  "site": "at://did:plc:oql6ds5vnff4ugar6rruliwd/site.standard.publication/3mn3ohu7oxx5w",
  "tags": [
    "G01C21/3833",
    "Korea Advanced Institute of Science and Technology"
  ],
  "textContent": "A processor includes a sampling unit configured to hierarchically sample a 2D image collected through any image collection device and pose information of the image collection device corresponding to the 2D image, and a rendering unit configured to perform SLAM through real-time rendering for data sampled by the sampling unit, wherein the rendering unit includes a computation core configured to perform a neural network operation based on a sparse expert model including a plurality of expert neural networks and reducing a number of neural network channels by exclusively activating an expert neural network differently selected for each input batch, and a scheduler configured to schedule a processing order of input batches to improve computational efficiency of the computation core.",
  "title": "PROCESSOR AND METHOD FOR SIMULTANEOUS LOCALIZATION AND MAPPING BASED ON REAL-TIME NEURAL NETWORK RENDERING USING SPARSE MIXTURE-OF-EXPERTS MODEL ACCELERATION ARCHITECTURE"
}