{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YXSSY5HLXIDGSADHJIAV2FJ7AH","short_pith_number":"pith:YXSSY5HL","schema_version":"1.0","canonical_sha256":"c5e52c74ebba066900674a015d153f01caa1089c8351a8eaac978b0d245c9b6a","source":{"kind":"arxiv","id":"2507.02546","version":1},"attestation_state":"computed","paper":{"title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MoGe-2 recovers metric-scale 3D point maps from single images while preserving relative accuracy and recovering fine details.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangzhong Sun, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng, Yue Dong, Zelong Lv","submitted_at":"2025-07-03T11:40:01Z","abstract_excerpt":"We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2507.02546","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T11:40:01Z","cross_cats_sorted":[],"title_canon_sha256":"69a4c31a1c4f93988564512ca314c607b2e13e3d74a903d61a230c5f492f3ee4","abstract_canon_sha256":"46d6c080246ee895c5b0b64f5fcd2d6b810ce47af3be30b136d59c0a34a3ec32"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:21.645751Z","signature_b64":"JHocDpYB3VHR4JkkiH1lh3xjof5+W1mrmwBJF6vPNMxJ4AcFYIhh/EXEA9d8dH/4EWyFcCu+xMl3IrJx7SSGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5e52c74ebba066900674a015d153f01caa1089c8351a8eaac978b0d245c9b6a","last_reissued_at":"2026-05-17T23:39:21.645140Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:21.645140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","license":"http://creativecommons.org/licenses/by/4.0/","headline":"MoGe-2 recovers metric-scale 3D point maps from single images while preserving relative accuracy and recovering fine details.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guangzhong Sun, Jianfeng Xiang, Jiaolong Yang, Ruicheng Wang, Sicheng Xu, Xin Tong, Yu Deng, Yue Dong, Zelong Lv","submitted_at":"2025-07-03T11:40:01Z","abstract_excerpt":"We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That filtering and completing real data with sharp synthetic labels preserves overall accuracy without introducing systematic biases or artifacts in the metric scale prediction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MoGe-2 recovers metric-scale 3D point maps from single images while preserving relative accuracy and recovering fine details.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c3d3708e42390f7c4efdc12ec35be462a375134cb79ddb30e2c1ac176e31d940"},"source":{"id":"2507.02546","kind":"arxiv","version":1},"verdict":{"id":"9bc5d1f1-9022-4657-a152-bde9404c4c96","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:16:02.251020Z","strongest_claim":"demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved.","one_line_summary":"MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That filtering and completing real data with sharp synthetic labels preserves overall accuracy without introducing systematic biases or artifacts in the metric scale prediction.","pith_extraction_headline":"MoGe-2 recovers metric-scale 3D point maps from single images while preserving relative accuracy and recovering fine details."},"references":{"count":83,"sample":[{"doi":"","year":2019,"title":"Apollo synthetic dataset, 2019","work_id":"8864ac7f-ef2c-45b4-8cb3-b1ddde64e709","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Zip-nerf: Anti- aliased grid-based neural radiance fields","work_id":"9639f894-6968-4677-bbb9-2ef05886e3a5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","work_id":"bdc2d9d8-b51a-48e3-afcf-bf862ee08c39","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Adabins: Depth estimation using adaptive bins","work_id":"4c9b0a43-3a22-4f30-8ab5-f2b1125fbbb9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","work_id":"c902e427-c54a-4fc4-8aef-d0243f90ea39","ref_index":5,"cited_arxiv_id":"2302.12288","is_internal_anchor":true}],"resolved_work":83,"snapshot_sha256":"780f7627cbc2a2b0ee91654468bc32caaefdebf0c97870c034e8013b257f366c","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4711f00f734e10caad460eaf929240113de1ce56ee645b3fa43300e30537ee54"},"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":"2507.02546","created_at":"2026-05-17T23:39:21.645227+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02546v1","created_at":"2026-05-17T23:39:21.645227+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02546","created_at":"2026-05-17T23:39:21.645227+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXSSY5HLXIDG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXSSY5HLXIDGSADH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXSSY5HL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":33,"internal_anchor_count":33,"sample":[{"citing_arxiv_id":"2504.19584","citing_title":"ShowMak3r: Compositional TV Show Reconstruction","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22629","citing_title":"H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01030","citing_title":"Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20820","citing_title":"AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21131","citing_title":"UniT: Unified Geometry Learning with Group Autoregressive Transformer","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17354","citing_title":"GeoHand: Unlocking Prior Geometry Knowledge for Monocular 3D Hand Reconstruction","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19797","citing_title":"Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19656","citing_title":"Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17340","citing_title":"Refracting Reality: Generating Images with Realistic Transparent Objects","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2511.19172","citing_title":"MetroGS: Efficient and Stable Reconstruction of Geometrically Accurate High-Fidelity Large-Scale Scenes","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15178","citing_title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14462","citing_title":"Real2Sim in HOI: Toward Physically Plausible HOI Reconstruction from Monocular Videos","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27105","citing_title":"UniDAC: Universal Metric Depth Estimation for Any Camera","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12774","citing_title":"WildPose: A Unified Framework for Robust Pose Estimation in the Wild","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2604.00813","citing_title":"DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02828","citing_title":"NavCrafter: Exploring 3D Scenes from a Single Image","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04135","citing_title":"NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11594","citing_title":"PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2507.13347","citing_title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27448","citing_title":"LA-Pose: Latent Action Pretraining Meets Pose Estimation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10922","citing_title":"Pixal3D: Pixel-Aligned 3D Generation from Images","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21915","citing_title":"Vista4D: Video Reshooting with 4D Point Clouds","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18336","citing_title":"Enhancing Glass Surface Reconstruction via Depth Prior for Robot Navigation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11097","citing_title":"CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11331","citing_title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH","json":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH.json","graph_json":"https://pith.science/api/pith-number/YXSSY5HLXIDGSADHJIAV2FJ7AH/graph.json","events_json":"https://pith.science/api/pith-number/YXSSY5HLXIDGSADHJIAV2FJ7AH/events.json","paper":"https://pith.science/paper/YXSSY5HL"},"agent_actions":{"view_html":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH","download_json":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH.json","view_paper":"https://pith.science/paper/YXSSY5HL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02546&json=true","fetch_graph":"https://pith.science/api/pith-number/YXSSY5HLXIDGSADHJIAV2FJ7AH/graph.json","fetch_events":"https://pith.science/api/pith-number/YXSSY5HLXIDGSADHJIAV2FJ7AH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH/action/storage_attestation","attest_author":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH/action/author_attestation","sign_citation":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH/action/citation_signature","submit_replication":"https://pith.science/pith/YXSSY5HLXIDGSADHJIAV2FJ7AH/action/replication_record"}},"created_at":"2026-05-17T23:39:21.645227+00:00","updated_at":"2026-05-17T23:39:21.645227+00:00"}