{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BQ32MVTKIX2DT7EN2EK6BGYHQS","short_pith_number":"pith:BQ32MVTK","schema_version":"1.0","canonical_sha256":"0c37a6566a45f439fc8dd115e09b07848c352b82c4c6fb11c7ac579724c93300","source":{"kind":"arxiv","id":"2303.15181","version":3},"attestation_state":"computed","paper":{"title":"DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Peng Dai, Ruihui Li, Xiaojuan Qi, Zhengzhe Liu","submitted_at":"2023-03-24T03:56:23Z","abstract_excerpt":"In this paper, we present a new text-guided 3D shape generation approach DreamStone that uses images as a stepping stone to bridge the gap between text and shape modalities for generating 3D shapes without requiring paired text and 3D data. The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistenc"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.15181","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-24T03:56:23Z","cross_cats_sorted":[],"title_canon_sha256":"088218eebc410793c9b6cf79824e1070d413a419e2b64f4b78a635b9c13f8574","abstract_canon_sha256":"7fa34252d146a7238f09ef5b5c693184111b37e70b9b53985b5fc57da695a5df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:15.540301Z","signature_b64":"oQpYfVJYpfoYv2lwblVLpkIaM0hirG/+gteeqWfTWS+UDynsPPOOyLAVNe1L+O/hrp/3S5QogfcWed9jlrMyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c37a6566a45f439fc8dd115e09b07848c352b82c4c6fb11c7ac579724c93300","last_reissued_at":"2026-07-05T06:54:15.539788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:15.539788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Peng Dai, Ruihui Li, Xiaojuan Qi, Zhengzhe Liu","submitted_at":"2023-03-24T03:56:23Z","abstract_excerpt":"In this paper, we present a new text-guided 3D shape generation approach DreamStone that uses images as a stepping stone to bridge the gap between text and shape modalities for generating 3D shapes without requiring paired text and 3D data. The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15181","kind":"arxiv","version":3},"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/2303.15181/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.15181","created_at":"2026-07-05T06:54:15.539859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.15181v3","created_at":"2026-07-05T06:54:15.539859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15181","created_at":"2026-07-05T06:54:15.539859+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ32MVTKIX2D","created_at":"2026-07-05T06:54:15.539859+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ32MVTKIX2DT7EN","created_at":"2026-07-05T06:54:15.539859+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ32MVTK","created_at":"2026-07-05T06:54:15.539859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09008","citing_title":"MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS","json":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS.json","graph_json":"https://pith.science/api/pith-number/BQ32MVTKIX2DT7EN2EK6BGYHQS/graph.json","events_json":"https://pith.science/api/pith-number/BQ32MVTKIX2DT7EN2EK6BGYHQS/events.json","paper":"https://pith.science/paper/BQ32MVTK"},"agent_actions":{"view_html":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS","download_json":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS.json","view_paper":"https://pith.science/paper/BQ32MVTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.15181&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ32MVTKIX2DT7EN2EK6BGYHQS/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ32MVTKIX2DT7EN2EK6BGYHQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS/action/storage_attestation","attest_author":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS/action/author_attestation","sign_citation":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS/action/citation_signature","submit_replication":"https://pith.science/pith/BQ32MVTKIX2DT7EN2EK6BGYHQS/action/replication_record"}},"created_at":"2026-07-05T06:54:15.539859+00:00","updated_at":"2026-07-05T06:54:15.539859+00:00"}