{
  "annotation_id": "629ea227-473d-42c7-8406-aa20af2e70b9",
  "date_created": "2026-02-17T05:53:19.851000Z",
  "date_modified": "2026-02-17T05:53:19.851000Z",
  "file_hash": "002740b48edd7d90089ddae3de55e04471eb35e9344ef0238b8f55e4709543a3",
  "private": false,
  "record": {
    "abstract": "This paper addresses the problem of affordance grounding from RGBD images of an object, which aims to localize surface regions corresponding to a text query that describes an action on the object. While existing methods predict affordance regions only on visible surfaces, we propose Affostruction, a generative framework that reconstructs complete geometry from partial observations and grounds affordances on the full shape including unobserved regions. We make three core contributions: generative multi-view reconstruction via sparse voxel fusion that extrapolates unseen geometry while maintaining constant token complexity, flow-based affordance grounding that captures inherent ambiguity in affordance distributions, and affordance-driven active view selection that leverages predicted affordances for intelligent viewpoint sampling. Affostruction achieves 19.1 aIoU on affordance grounding (40.4\\% improvement) and 32.67 IoU for 3D reconstruction (67.7\\% improvement), enabling accurate affordance prediction on complete shapes.",
    "arxiv_id": "2601.09211",
    "authors": [
      "Chunghyun Park",
      "Seunghyeon Lee",
      "Minsu Cho"
    ],
    "categories": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Affostruction: 3D Affordance Grounding with Generative Reconstruction",
    "url": "https://arxiv.org/abs/2601.09211",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "50b107ec-ec02-42ef-9ce7-8fe94292f77c",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}