{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GWZP4T3473LA3RMFQMWXADLXAS","short_pith_number":"pith:GWZP4T34","schema_version":"1.0","canonical_sha256":"35b2fe4f7cfed60dc585832d700d7704b2c71fb00f206d09d6f913780d274588","source":{"kind":"arxiv","id":"2603.05999","version":2},"attestation_state":"computed","paper":{"title":"RePer-360: Releasing Perspective Priors for 360$^\\circ$ Depth Estimation via Self-Modulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Guan, Chunyu Lin, Jiyuan Wang, Junsong Zhang, Zhijie Shen","submitted_at":"2026-03-06T07:58:53Z","abstract_excerpt":"Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360$^\\circ$ images due to the substantial geometric discrepancy between perspective and panoramic domains. Moreover, fully fine-tuning these models typically requires large amounts of panoramic data. To address this issue, we propose RePer-360, a distortion-aware self-modulation framework for monocular panoramic depth estimation that adapts depth foundation models while preserving powerful pretrained perspective priors. Specifically, we design a lightweight geometry-aligned guidan"},"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":"2603.05999","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-06T07:58:53Z","cross_cats_sorted":[],"title_canon_sha256":"5f5238769f23a334da4fb2cc7915d343d27d44da2cff6648328b34f516cc2e56","abstract_canon_sha256":"32c78a74b59fb4f253219c14ed64460f8de103832dfffd526150a2b7fa1837bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:17.536932Z","signature_b64":"/0hnWeMZcwTdhUcmukLsIszLb/5jQ9xyzaHKPtLUVnnG6TqTM9VInpzjwBhw8MVehKFdwxddVY1USDvLSRJbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b2fe4f7cfed60dc585832d700d7704b2c71fb00f206d09d6f913780d274588","last_reissued_at":"2026-06-30T02:17:17.535986Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:17.535986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RePer-360: Releasing Perspective Priors for 360$^\\circ$ Depth Estimation via Self-Modulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cheng Guan, Chunyu Lin, Jiyuan Wang, Junsong Zhang, Zhijie Shen","submitted_at":"2026-03-06T07:58:53Z","abstract_excerpt":"Recent depth foundation models trained on perspective imagery achieve strong performance, yet generalize poorly to 360$^\\circ$ images due to the substantial geometric discrepancy between perspective and panoramic domains. Moreover, fully fine-tuning these models typically requires large amounts of panoramic data. To address this issue, we propose RePer-360, a distortion-aware self-modulation framework for monocular panoramic depth estimation that adapts depth foundation models while preserving powerful pretrained perspective priors. Specifically, we design a lightweight geometry-aligned guidan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05999","kind":"arxiv","version":2},"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/2603.05999/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":"2603.05999","created_at":"2026-06-30T02:17:17.536105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.05999v2","created_at":"2026-06-30T02:17:17.536105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05999","created_at":"2026-06-30T02:17:17.536105+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWZP4T3473LA","created_at":"2026-06-30T02:17:17.536105+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWZP4T3473LA3RMF","created_at":"2026-06-30T02:17:17.536105+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWZP4T34","created_at":"2026-06-30T02:17:17.536105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.11723","citing_title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS","json":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS.json","graph_json":"https://pith.science/api/pith-number/GWZP4T3473LA3RMFQMWXADLXAS/graph.json","events_json":"https://pith.science/api/pith-number/GWZP4T3473LA3RMFQMWXADLXAS/events.json","paper":"https://pith.science/paper/GWZP4T34"},"agent_actions":{"view_html":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS","download_json":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS.json","view_paper":"https://pith.science/paper/GWZP4T34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.05999&json=true","fetch_graph":"https://pith.science/api/pith-number/GWZP4T3473LA3RMFQMWXADLXAS/graph.json","fetch_events":"https://pith.science/api/pith-number/GWZP4T3473LA3RMFQMWXADLXAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS/action/storage_attestation","attest_author":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS/action/author_attestation","sign_citation":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS/action/citation_signature","submit_replication":"https://pith.science/pith/GWZP4T3473LA3RMFQMWXADLXAS/action/replication_record"}},"created_at":"2026-06-30T02:17:17.536105+00:00","updated_at":"2026-06-30T02:17:17.536105+00:00"}