{
  "$schema": "https://themachinepress.com/schemas/story-v1.schema.json",
  "schema_version": "1.0.0",
  "document_type": "machine_press_story",
  "story": {
    "story_id": "mp-2026-11-11-008",
    "source_story_id": "tmp-story-ugg-generative-geometry",
    "edition_id": "mp-2026-11-11-morning-0124",
    "edition_url": "https://themachinepress.com/edition/2026-11-11",
    "position": 8,
    "story_type": "dispatch",
    "section": "frontier-models",
    "editorial_classification": "editorial",
    "headline": "One Model Completes Both the Picture and Its Geometry",
    "slug": "one-model-completes-both-the-picture-and-its-geometry",
    "dek": "UGG treats video, depth and camera pose as partially observed pieces of the same four-dimensional scene.",
    "summary": "UGG treats video, depth and camera pose as partially observed pieces of the same four-dimensional scene.",
    "body_text": "UGG combines RGB video with depth and camera pose in one generative framework for four-dimensional scene understanding. Different noise levels across modality and time let the model formulate visual synthesis and geometric prediction as conditional completion, so it can train across datasets that expose different subsets of annotation. At inference, it searches multiple plausible scene hypotheses and uses geometric evidence extracted from observed frames to improve predictions. The authors report gains over separate baselines in camera-controlled generation, depth estimation and pose prediction, including sparse-observation settings.",
    "why_it_matters": "UGG treats video, depth and camera pose as partially observed pieces of the same four-dimensional scene.",
    "limitations": [],
    "importance": 7,
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-11-008/one-model-completes-both-the-picture-and-its-geometry",
    "json_url": "https://themachinepress.com/story/mp-2026-11-11-008.json",
    "first_published_at": "2026-11-11T09:00:00.000-05:00",
    "modified_at": "2026-11-11T09:00:00.000-05:00",
    "content_status": "new",
    "is_carryover": false,
    "carryover_reason": null,
    "key_claims": [
      {
        "claim_id": "claim-mp-2026-11-11-008-001",
        "text": "UGG treats video, depth and camera pose as partially observed pieces of the same four-dimensional scene.",
        "source_ids": [
          "source-2026-11-11-008"
        ],
        "qualification": null
      }
    ],
    "source_ids": [
      "source-2026-11-11-008"
    ],
    "tags": [
      "ugg",
      "unified",
      "generative",
      "geometry",
      "model"
    ],
    "image_url": "https://themachinepress.com/issues/2026-11-11/ugg-wireframe.webp",
    "corrections": []
  },
  "sources": [
    {
      "source_id": "source-2026-11-11-008",
      "title": "arXiv:2611.14440v1",
      "publisher": "arXiv / Cornell University",
      "url": "https://arxiv.org/abs/2611.14440v1",
      "canonical_url": "https://arxiv.org/abs/2611.14440v1",
      "source_type": "primary_research",
      "is_primary_source": true,
      "published_at": "2026-11-10T13:11:40.000-05:00",
      "accessed_at": "2026-11-11T08:26:32.531-05:00",
      "supports_claim_ids": [
        "claim-mp-2026-11-11-008-001"
      ]
    }
  ],
  "corrections": [],
  "publisher": {
    "name": "The Machine Press",
    "url": "https://themachinepress.com",
    "description": "A daily newspaper for the age of artificial intelligence."
  },
  "cite_this_report": {
    "title": "One Model Completes Both the Picture and Its Geometry",
    "publisher": "The Machine Press",
    "published_at": "2026-11-11T09:00:00.000-05:00",
    "canonical_url": "https://themachinepress.com/story/mp-2026-11-11-008/one-model-completes-both-the-picture-and-its-geometry"
  }
}