{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YKK344BOP3XHMEWCKLB426GZKM","short_pith_number":"pith:YKK344BO","schema_version":"1.0","canonical_sha256":"c295be702e7eee7612c252c3cd78d9531f16793e6d91675b50f8dc5235f00f72","source":{"kind":"arxiv","id":"2412.18605","version":1},"attestation_state":"computed","paper":{"title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Du, Hengshuang Zhao, Tianyu Pang, Zehan Wang, Zhou Zhao, Ziang Zhang","submitted_at":"2024-12-24T18:58:43Z","abstract_excerpt":"Orientation is a key attribute of objects, crucial for understanding their spatial pose and arrangement in images. However, practical solutions for accurate orientation estimation from a single image remain underexplored. In this work, we introduce Orient Anything, the first expert and foundational model designed to estimate object orientation in a single- and free-view image. Due to the scarcity of labeled data, we propose extracting knowledge from the 3D world. By developing a pipeline to annotate the front face of 3D objects and render images from random views, we collect 2M images with pre"},"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":"2412.18605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"5c103b743d026924f061b526868800d9a17d9f08a371b7c43c5a6abb7a9c1f56","abstract_canon_sha256":"8e2c00f8610f2f1decbecd008a82d847b560476e438c83338216da3870d1dd43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:58.104840Z","signature_b64":"lKg1lKqlYUx6OxKmheG05nNhzqKZqq8SgGgz3kwah7eNbStf5EfsA/oGTWiQ2rU22BDUBkOgUOhijffoPy8sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c295be702e7eee7612c252c3cd78d9531f16793e6d91675b50f8dc5235f00f72","last_reissued_at":"2026-07-05T09:53:58.104397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:58.104397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orient Anything: Learning Robust Object Orientation Estimation from Rendering 3D Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Du, Hengshuang Zhao, Tianyu Pang, Zehan Wang, Zhou Zhao, Ziang Zhang","submitted_at":"2024-12-24T18:58:43Z","abstract_excerpt":"Orientation is a key attribute of objects, crucial for understanding their spatial pose and arrangement in images. However, practical solutions for accurate orientation estimation from a single image remain underexplored. In this work, we introduce Orient Anything, the first expert and foundational model designed to estimate object orientation in a single- and free-view image. Due to the scarcity of labeled data, we propose extracting knowledge from the 3D world. By developing a pipeline to annotate the front face of 3D objects and render images from random views, we collect 2M images with pre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18605","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/2412.18605/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":"2412.18605","created_at":"2026-07-05T09:53:58.104453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18605v1","created_at":"2026-07-05T09:53:58.104453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18605","created_at":"2026-07-05T09:53:58.104453+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKK344BOP3XH","created_at":"2026-07-05T09:53:58.104453+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKK344BOP3XHMEWC","created_at":"2026-07-05T09:53:58.104453+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKK344BO","created_at":"2026-07-05T09:53:58.104453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22694","citing_title":"SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30058","citing_title":"Emergence of a Shared Canonical Object Frame from In-the-Wild Videos","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28270","citing_title":"Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17812","citing_title":"ChopGrad: Pixel-Wise Losses for Latent Video Diffusion via Truncated Backpropagation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19257","citing_title":"Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM","json":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM.json","graph_json":"https://pith.science/api/pith-number/YKK344BOP3XHMEWCKLB426GZKM/graph.json","events_json":"https://pith.science/api/pith-number/YKK344BOP3XHMEWCKLB426GZKM/events.json","paper":"https://pith.science/paper/YKK344BO"},"agent_actions":{"view_html":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM","download_json":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM.json","view_paper":"https://pith.science/paper/YKK344BO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18605&json=true","fetch_graph":"https://pith.science/api/pith-number/YKK344BOP3XHMEWCKLB426GZKM/graph.json","fetch_events":"https://pith.science/api/pith-number/YKK344BOP3XHMEWCKLB426GZKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM/action/storage_attestation","attest_author":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM/action/author_attestation","sign_citation":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM/action/citation_signature","submit_replication":"https://pith.science/pith/YKK344BOP3XHMEWCKLB426GZKM/action/replication_record"}},"created_at":"2026-07-05T09:53:58.104453+00:00","updated_at":"2026-07-05T09:53:58.104453+00:00"}