{
  "docId": "019dd923-5e88-73ef-bd5c-f812573a947a",
  "docSlug": "eea7524c557036f4",
  "documentTitle": "2020 Air Street Capital The State of AI Report 2020",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 50,
  "pageCount": 177,
  "prevPage": 49,
  "nextPage": 51,
  "slideType": "industry_trends",
  "function": "present_framework",
  "density": "balanced",
  "nDataPoints": 0,
  "notes": "The slide illustrates a technical process flow for AI training data generation.",
  "elementsJson": [
    "bullet_list",
    "process_diagram"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f812573a947a/50",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a#slide-50",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Here, single image depth prediction networks (monodepth) can be used to convert any single image into training data for stereo networks.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c5-73ac-aa64-8bc4ebd924c0",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.55,
        "x": 0.42,
        "y": 0.35
      },
      "kind": "diagram",
      "text": "Process flow showing Data generation and Stereo training stages",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9f225924-a457-409f-ad3f-2851f239e2b8",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.4,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "list",
      "text": "Training state-of-the-art stereo matching networks on a collection of single images.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0fe11845-b6e7-458f-937e-a849e31d5898",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.4,
        "w": 0.4,
        "x": 0.02,
        "y": 0.29
      },
      "kind": "paragraph",
      "text": "Stereo matching networks estimate depth from a calibrated stereo pair of images. Training data for such networks requires left and right image pair and ground truth depth. Such data is very difficult to collect, involving special hardware like LiDAR as well as careful calibration and synchronization of cameras. Here, single image depth prediction networks (monodepth) can be used to convert any single image into training data for stereo networks.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "f47290fd-ecf9-4ccf-a050-6ba58bb95400",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.45,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Computer vision learns stereo from single images",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a5163e6d-339b-4625-8bec-173f1abd8eea",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Process flow",
      "slug": "process-flow",
      "agent": null,
      "layer": "slide",
      "matchId": "c6cb1007-d2be-4e0a-a8d5-e489f3e362c8",
      "evidence": "Process flow showing Data generation and Stereo training stages",
      "confidence": 0.8
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-ed2a8f38a754",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Research, Talent, Industry sections inventory what happened in AI in 2020.",
      "position": 1,
      "confidence": 60,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-fc384f439bba",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Talent and Industry sections build momentum of AI progress.",
      "position": 2,
      "confidence": 40,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 57,
      "from": 47,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3c-f820616b6fcc",
      "evidence": "Wimbledon synth video, object detection, depth, AutoML-Zero examples in sequence.",
      "position": 5,
      "objective": "Catalog computer vision and generative model advances",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 70,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}