{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WKOY7H5WJBQTPVVNMKTEELZOXY","short_pith_number":"pith:WKOY7H5W","schema_version":"1.0","canonical_sha256":"b29d8f9fb6486137d6ad62a6422f2ebe25c4db7ded1a4f2b55a1c878a0167f0c","source":{"kind":"arxiv","id":"2410.19115","version":3},"attestation_state":"computed","paper":{"title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cassie Dai, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng","submitted_at":"2024-10-24T19:29:02Z","abstract_excerpt":"We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is agnostic to true global scale and shift. This new representation precludes ambiguous supervision in training and facilitate effective geometry learning. Furthermore, we propose a set of novel global and local geometry supervisions that empower the model to learn high-quality geometry. These include a robust, optimal, and efficient point cloud alignment solver for a"},"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":"2410.19115","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T19:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"9f324e993e19af2322bff0339ba09a35c84d682ecfd9bd75d1f547909a9e94b5","abstract_canon_sha256":"0741441dd7b9c13204103dd86995f0aa608cf6c0946d46ea1208c237ba14622d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:10.380306Z","signature_b64":"U1ff3dFtosZY9p5+e3klj5GBodj8buSdULCtjamlA0mtar+IWLExqR9B0J9PMFvnxzHecg+lX8hAXSBTHprJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b29d8f9fb6486137d6ad62a6422f2ebe25c4db7ded1a4f2b55a1c878a0167f0c","last_reissued_at":"2026-07-05T10:49:10.379832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:10.379832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cassie Dai, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng","submitted_at":"2024-10-24T19:29:02Z","abstract_excerpt":"We present MoGe, a powerful model for recovering 3D geometry from monocular open-domain images. Given a single image, our model directly predicts a 3D point map of the captured scene with an affine-invariant representation, which is agnostic to true global scale and shift. This new representation precludes ambiguous supervision in training and facilitate effective geometry learning. Furthermore, we propose a set of novel global and local geometry supervisions that empower the model to learn high-quality geometry. These include a robust, optimal, and efficient point cloud alignment solver for a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19115","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/2410.19115/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":"2410.19115","created_at":"2026-07-05T10:49:10.379889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19115v3","created_at":"2026-07-05T10:49:10.379889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19115","created_at":"2026-07-05T10:49:10.379889+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKOY7H5WJBQT","created_at":"2026-07-05T10:49:10.379889+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKOY7H5WJBQTPVVN","created_at":"2026-07-05T10:49:10.379889+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKOY7H5W","created_at":"2026-07-05T10:49:10.379889+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08771","citing_title":"ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18426","citing_title":"VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15195","citing_title":"VGGT-$\\Omega$","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28735","citing_title":"SeeGroup: Multi-Layer Depth Estimation of Transparent Surfaces via Self-Determined Grouping","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18599","citing_title":"Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17411","citing_title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY","json":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY.json","graph_json":"https://pith.science/api/pith-number/WKOY7H5WJBQTPVVNMKTEELZOXY/graph.json","events_json":"https://pith.science/api/pith-number/WKOY7H5WJBQTPVVNMKTEELZOXY/events.json","paper":"https://pith.science/paper/WKOY7H5W"},"agent_actions":{"view_html":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY","download_json":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY.json","view_paper":"https://pith.science/paper/WKOY7H5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19115&json=true","fetch_graph":"https://pith.science/api/pith-number/WKOY7H5WJBQTPVVNMKTEELZOXY/graph.json","fetch_events":"https://pith.science/api/pith-number/WKOY7H5WJBQTPVVNMKTEELZOXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY/action/storage_attestation","attest_author":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY/action/author_attestation","sign_citation":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY/action/citation_signature","submit_replication":"https://pith.science/pith/WKOY7H5WJBQTPVVNMKTEELZOXY/action/replication_record"}},"created_at":"2026-07-05T10:49:10.379889+00:00","updated_at":"2026-07-05T10:49:10.379889+00:00"}