{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VLBOM5IW7QH2WA3SYXKWF7CPME","short_pith_number":"pith:VLBOM5IW","schema_version":"1.0","canonical_sha256":"aac2e67516fc0fab0372c5d562fc4f61369b657dbb5d2336b53ce7cc00e60af2","source":{"kind":"arxiv","id":"2507.12462","version":2},"attestation_state":"computed","paper":{"title":"SpatialTrackerV2: 3D Point Tracking Made Easy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Hujun Bao, Jianyuan Wang, Nan Xue, Nikita Karaev, Xiaowei Zhou, Xing Zhu, Yujun Shen, Yuri Makarov, Yuxi Xiao","submitted_at":"2025-07-16T17:59:03Z","abstract_excerpt":"We present SpatialTrackerV2, a feed-forward 3D point tracking method for monocular videos. Going beyond modular pipelines built on off-the-shelf components for 3D tracking, our approach unifies the intrinsic connections between point tracking, monocular depth, and camera pose estimation into a high-performing and feedforward 3D point tracker. It decomposes world-space 3D motion into scene geometry, camera ego-motion, and pixel-wise object motion, with a fully differentiable and end-to-end architecture, allowing scalable training across a wide range of datasets, including synthetic sequences, p"},"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":"2507.12462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-16T17:59:03Z","cross_cats_sorted":[],"title_canon_sha256":"39cd30be39d28dcb3f47d4cbee5fcbb5e9fb36a6ae4563383ed3a50410e6840e","abstract_canon_sha256":"fe6e002bd53ef0b55f2a19a27ef9bb99cd53c5c96125079d2d170ea10ddda0e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:01.596884Z","signature_b64":"U6xceznxEaaL5nQNMoJnp2VbsLwVnUdVcjX6bMoc51rznZzkiq8Bf5x287NaaplvFbpTc0XXsHhKRZ0rsZk3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aac2e67516fc0fab0372c5d562fc4f61369b657dbb5d2336b53ce7cc00e60af2","last_reissued_at":"2026-07-05T11:40:01.596373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:01.596373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpatialTrackerV2: 3D Point Tracking Made Easy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyi Kang, Hujun Bao, Jianyuan Wang, Nan Xue, Nikita Karaev, Xiaowei Zhou, Xing Zhu, Yujun Shen, Yuri Makarov, Yuxi Xiao","submitted_at":"2025-07-16T17:59:03Z","abstract_excerpt":"We present SpatialTrackerV2, a feed-forward 3D point tracking method for monocular videos. Going beyond modular pipelines built on off-the-shelf components for 3D tracking, our approach unifies the intrinsic connections between point tracking, monocular depth, and camera pose estimation into a high-performing and feedforward 3D point tracker. It decomposes world-space 3D motion into scene geometry, camera ego-motion, and pixel-wise object motion, with a fully differentiable and end-to-end architecture, allowing scalable training across a wide range of datasets, including synthetic sequences, p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12462","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/2507.12462/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":"2507.12462","created_at":"2026-07-05T11:40:01.596436+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12462v2","created_at":"2026-07-05T11:40:01.596436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12462","created_at":"2026-07-05T11:40:01.596436+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLBOM5IW7QH2","created_at":"2026-07-05T11:40:01.596436+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLBOM5IW7QH2WA3S","created_at":"2026-07-05T11:40:01.596436+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLBOM5IW","created_at":"2026-07-05T11:40:01.596436+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08436","citing_title":"EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25344","citing_title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27345","citing_title":"RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19333","citing_title":"Do as I Do: Dexterous Manipulation Data from Everyday Human Videos","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18558","citing_title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17310","citing_title":"SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08103","citing_title":"Revisiting Articulated Parts Perception in Robot Manipulation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27345","citing_title":"RayPE: Ray-Space Positional Encoding for 3D-Aware Video Generation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22272","citing_title":"Imagine2Real: Towards Zero-shot Humanoid-Object Interaction via Video Generative Priors","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19786","citing_title":"Fast 4D Mesh Generation by Spatio-Temporal Attention Chains","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12587","citing_title":"TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12027","citing_title":"4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09366","citing_title":"Robust 4D Visual Geometry Transformer with Uncertainty-Aware Priors","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07990","citing_title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME","json":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME.json","graph_json":"https://pith.science/api/pith-number/VLBOM5IW7QH2WA3SYXKWF7CPME/graph.json","events_json":"https://pith.science/api/pith-number/VLBOM5IW7QH2WA3SYXKWF7CPME/events.json","paper":"https://pith.science/paper/VLBOM5IW"},"agent_actions":{"view_html":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME","download_json":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME.json","view_paper":"https://pith.science/paper/VLBOM5IW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12462&json=true","fetch_graph":"https://pith.science/api/pith-number/VLBOM5IW7QH2WA3SYXKWF7CPME/graph.json","fetch_events":"https://pith.science/api/pith-number/VLBOM5IW7QH2WA3SYXKWF7CPME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME/action/storage_attestation","attest_author":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME/action/author_attestation","sign_citation":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME/action/citation_signature","submit_replication":"https://pith.science/pith/VLBOM5IW7QH2WA3SYXKWF7CPME/action/replication_record"}},"created_at":"2026-07-05T11:40:01.596436+00:00","updated_at":"2026-07-05T11:40:01.596436+00:00"}