{"paper":{"title":"Holo-Captioning: Toward the Text Equivalent of 3D Scenes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengke Bu, Kai Han, Kun-Yu Lin, Zhenguo Li","submitted_at":"2026-07-03T03:14:17Z","abstract_excerpt":"This work introduces holo-captioning, a novel task that strives to seek the text equivalent of 3D scenes. As the initial step, we formulate holo-captioning as generating a structured textual description that comprehensively depicts all entities within a 3D scene -- including their semantic tags, spatial locations, attributes, and inter-entity relations. To tackle this challenging task, we first develop an effective captioning engine to produce detailed descriptions of individual entity instances and instance pairs, and contribute a large-scale benchmark comprising over 15K scenes for training "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02908","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.02908/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}