{
  "id": 9068356,
  "title": "AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos",
  "url": "https://urgent.news/2026/09/21/agentstar-agentic-shape-tracking-and-reconstruction-from-monocular",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-21T12:26:13.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.24487v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first estimate dense pixel correspondences and then recover object motion from them, our method infers a structured 3D object model, including its geometry and kinematic structure, and uses this model to optimise object track estimates over time. In our…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}