{
  "docId": "019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "docSlug": "bf350dd574c19997",
  "documentTitle": "2021 Air Street Capital The State of AI Report 2021",
  "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": 18,
  "pageCount": 188,
  "prevPage": 17,
  "nextPage": 19,
  "slideType": "industry_trends",
  "function": "summarize",
  "density": "dense",
  "nDataPoints": 0,
  "notes": "The slide explains the technical mechanism of NeRF and mentions GIRAFFE as a generative variant.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "process_diagram",
    "photo",
    "logo_grid"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-fd5012384ae3/18",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3#slide-18",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Neural Radiance Fields (NeRF) already achieves SOTA results on view synthesis. New applications further highlight how impressive it is.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d24-588471ef0cd9",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.38,
        "x": 0.58,
        "y": 0.68
      },
      "kind": "image",
      "text": "360 degree car rotation example.",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7810edc6-6a13-45b6-bdcb-9bf3749507f7",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.38,
        "x": 0.58,
        "y": 0.48
      },
      "kind": "image",
      "text": "Visual examples of rotating objects and adding objects.",
      "attrs": null,
      "subkind": "illustration",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9d06f168-4b0b-490e-9bfc-a7bf76a498d7",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.35,
        "x": 0.6,
        "y": 0.28
      },
      "kind": "image",
      "text": "NeRF process diagram showing input images, optimization, and rendering.",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "55247986-d884-4805-a40e-f16eff6dc060",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.55,
        "x": 0.02,
        "y": 0.32
      },
      "kind": "list",
      "text": "Given multiple views of an image, NeRF uses a multilayered perceptron to learn a representation of the image and to render new views of it. It learns a mapping from every pixel location and view direction to the color and density at that location.\nNeRF outperforms previous work on datasets of both synthetic and real images. It has also found a powerful application in disentangled image generation — the task of controlling one or more attributes of an image, for example translating or rotating objects without changing the background.\nGIRAFFE uses a generative variant of NeRF to represent objects in images without the need for supervision through camera poses. But instead of modeling the entire scene with an MLP, GIRAFFE does this for each object.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "50d9e844-b5a8-4cd6-8913-9dd144bf8507",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.07,
        "w": 0.55,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "Neural Radiance Fields (NeRF) already achieves SOTA results on view synthesis. New applications further highlight how impressive it is.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c27a3bf2-5763-468c-b25d-9ceddf4b6580",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.45,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Remarkable progress in Novel View Synthesis",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0d83ccdd-48e4-4461-baf2-83cd5fa69905",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Before-After-Bridge",
      "slug": "before-after-bridge",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "85c90a8b-896c-46ac-9b0e-05cf2775fc95",
      "evidence": "The slide shows a process diagram of NeRF, highlighting the 'before' (input images) and 'after' (rendering new views) aspects.",
      "confidence": 0.7
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 152,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-0affbadec38e",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions p.5-6, Exec Summary p.7, then Sections 1-3 catalog evidence.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 152,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e35-1b3ee3a1c012",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Three sections accumulating evidence of accelerating progress.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 18,
      "from": 11,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-45052222b756",
      "evidence": "Multiple evidence slides (vision, audio, 3D, MLPs comeback) all converging on transformer dominance.",
      "position": 2,
      "objective": "Show transformers spreading across AI domains",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 82,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}