{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LF6ISFLGTRQP2SZGOQQLGB34YF","short_pith_number":"pith:LF6ISFLG","schema_version":"1.0","canonical_sha256":"597c8915669c60fd4b267420b3077cc15b294d6b0d329f20246fbc8905d14aee","source":{"kind":"arxiv","id":"2503.05638","version":1},"attestation_state":"computed","paper":{"title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Jinbo Xing, Mark YU, Wenbo Hu, Ying Shan","submitted_at":"2025-03-07T17:57:53Z","abstract_excerpt":"We present TrajectoryCrafter, a novel approach to redirect camera trajectories for monocular videos. By disentangling deterministic view transformations from stochastic content generation, our method achieves precise control over user-specified camera trajectories. We propose a novel dual-stream conditional video diffusion model that concurrently integrates point cloud renders and source videos as conditions, ensuring accurate view transformations and coherent 4D content generation. Instead of leveraging scarce multi-view videos, we curate a hybrid training dataset combining web-scale monocula"},"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":"2503.05638","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-07T17:57:53Z","cross_cats_sorted":["cs.AI","cs.GR"],"title_canon_sha256":"4a6c5a4ed3351b2813a1694a8c13ff62ba2cc60dc0a2ec5edf082f9ec230d1cc","abstract_canon_sha256":"9251a8475bbb8ee4f32286785fc9df93108365c67b17459ce3e8c292668283ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:33.599924Z","signature_b64":"J3bpmI8wNIT2em+xHGyW17Vvxm1rIFmqf2s0wx2UsIHMzw/04wlI/5rKt+F5JfzcniumeyH1TkQU9TMrWx2eDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"597c8915669c60fd4b267420b3077cc15b294d6b0d329f20246fbc8905d14aee","last_reissued_at":"2026-07-05T10:26:33.598991Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:33.598991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.GR"],"primary_cat":"cs.CV","authors_text":"Jinbo Xing, Mark YU, Wenbo Hu, Ying Shan","submitted_at":"2025-03-07T17:57:53Z","abstract_excerpt":"We present TrajectoryCrafter, a novel approach to redirect camera trajectories for monocular videos. By disentangling deterministic view transformations from stochastic content generation, our method achieves precise control over user-specified camera trajectories. We propose a novel dual-stream conditional video diffusion model that concurrently integrates point cloud renders and source videos as conditions, ensuring accurate view transformations and coherent 4D content generation. Instead of leveraging scarce multi-view videos, we curate a hybrid training dataset combining web-scale monocula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.05638","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/2503.05638/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":"2503.05638","created_at":"2026-07-05T10:26:33.599124+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.05638v1","created_at":"2026-07-05T10:26:33.599124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.05638","created_at":"2026-07-05T10:26:33.599124+00:00"},{"alias_kind":"pith_short_12","alias_value":"LF6ISFLGTRQP","created_at":"2026-07-05T10:26:33.599124+00:00"},{"alias_kind":"pith_short_16","alias_value":"LF6ISFLGTRQP2SZG","created_at":"2026-07-05T10:26:33.599124+00:00"},{"alias_kind":"pith_short_8","alias_value":"LF6ISFLG","created_at":"2026-07-05T10:26:33.599124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23105","citing_title":"Compression and Retrieval: Implicit Memory Retrieval for Video World Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17310","citing_title":"SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09187","citing_title":"CP4D: Compositional Physics-aware 4D Scene Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07508","citing_title":"Streaming Video Generation with Streaming Force Control","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00832","citing_title":"Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01590","citing_title":"Effective Multi-sensor Conditioning for Street-view Novel-view Synthesis","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22481","citing_title":"Lighting-Consistent Object Transfer Across Radiance Fields","ref_index":266,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24764","citing_title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24764","citing_title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2512.17445","citing_title":"LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10934","citing_title":"ViPE: Video Pose Engine for 3D Geometric Perception","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12957","citing_title":"GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12119","citing_title":"MoCam: Unified Novel View Synthesis via Structured Denoising Dynamics","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11367","citing_title":"3D-Belief: Embodied Belief Inference via Generative 3D World Modeling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24764","citing_title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21914","citing_title":"VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12270","citing_title":"DreamStereo: Towards Real-Time Stereo Inpainting for HD Videos","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09429","citing_title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06010","citing_title":"OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21776","citing_title":"Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF","json":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF.json","graph_json":"https://pith.science/api/pith-number/LF6ISFLGTRQP2SZGOQQLGB34YF/graph.json","events_json":"https://pith.science/api/pith-number/LF6ISFLGTRQP2SZGOQQLGB34YF/events.json","paper":"https://pith.science/paper/LF6ISFLG"},"agent_actions":{"view_html":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF","download_json":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF.json","view_paper":"https://pith.science/paper/LF6ISFLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.05638&json=true","fetch_graph":"https://pith.science/api/pith-number/LF6ISFLGTRQP2SZGOQQLGB34YF/graph.json","fetch_events":"https://pith.science/api/pith-number/LF6ISFLGTRQP2SZGOQQLGB34YF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF/action/storage_attestation","attest_author":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF/action/author_attestation","sign_citation":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF/action/citation_signature","submit_replication":"https://pith.science/pith/LF6ISFLGTRQP2SZGOQQLGB34YF/action/replication_record"}},"created_at":"2026-07-05T10:26:33.599124+00:00","updated_at":"2026-07-05T10:26:33.599124+00:00"}