{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z4TYGHSZR4NNLFLNDU2UNY5EZ7","short_pith_number":"pith:Z4TYGHSZ","schema_version":"1.0","canonical_sha256":"cf27831e598f1ad5956d1d3546e3a4cfd32141759ac3debb9200dfb0f94534fa","source":{"kind":"arxiv","id":"2406.16863","version":1},"attestation_state":"computed","paper":{"title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Qiu, Menghan Xia, Yingqing He, Zhaoxi Chen, Zhouxia Wang, Ziwei Liu","submitted_at":"2024-06-24T17:59:56Z","abstract_excerpt":"Diffusion model has demonstrated remarkable capability in video generation, which further sparks interest in introducing trajectory control into the generation process. While existing works mainly focus on training-based methods (e.g., conditional adapter), we argue that diffusion model itself allows decent control over the generated content without requiring any training. In this study, we introduce a tuning-free framework to achieve trajectory-controllable video generation, by imposing guidance on both noise construction and attention computation. Specifically, 1) we first show several instr"},"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":"2406.16863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"c25602eea0ddc5880ce01768c0ed099277770dff28f736874ccd40154423fd5b","abstract_canon_sha256":"75e9f3fff581190bf4e9ebb612fb8db282e616b0c822452bc3ea1665d008d298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:04.716656Z","signature_b64":"Yt0EXs0mkjNYcLwqutOlqQn/36Pkz6sTwEWcX9A10tPmi0YGGhYWdmFDcGUpcIKHpyuI/smv5jEkSwsnd4mpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf27831e598f1ad5956d1d3546e3a4cfd32141759ac3debb9200dfb0f94534fa","last_reissued_at":"2026-07-05T08:36:04.716187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:04.716187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haonan Qiu, Menghan Xia, Yingqing He, Zhaoxi Chen, Zhouxia Wang, Ziwei Liu","submitted_at":"2024-06-24T17:59:56Z","abstract_excerpt":"Diffusion model has demonstrated remarkable capability in video generation, which further sparks interest in introducing trajectory control into the generation process. While existing works mainly focus on training-based methods (e.g., conditional adapter), we argue that diffusion model itself allows decent control over the generated content without requiring any training. In this study, we introduce a tuning-free framework to achieve trajectory-controllable video generation, by imposing guidance on both noise construction and attention computation. Specifically, 1) we first show several instr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16863","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/2406.16863/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":"2406.16863","created_at":"2026-07-05T08:36:04.716247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16863v1","created_at":"2026-07-05T08:36:04.716247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16863","created_at":"2026-07-05T08:36:04.716247+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4TYGHSZR4NN","created_at":"2026-07-05T08:36:04.716247+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4TYGHSZR4NNLFLN","created_at":"2026-07-05T08:36:04.716247+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4TYGHSZ","created_at":"2026-07-05T08:36:04.716247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20891","citing_title":"Go-with-the-Track: Video Compositing and Motion Control with Point Tracking","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18066","citing_title":"NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01869","citing_title":"QWERTY: Training-Free Motion Control via Query-Warped Video Diffusion Transformers","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00861","citing_title":"TrajLoc: Trajectory-Attention Localization for Multi-Object Motion Control","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15042","citing_title":"EverAnimate: Minute-Scale Human Animation via Latent Flow Restoration","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18066","citing_title":"NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22996","citing_title":"CoMoGen: COntrollable MOtion Dynamics and Interactions with Mask-Guided Video GENeration","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2601.01955","citing_title":"MotionAdapter: Video Motion Transfer via Content-Aware Attention Customization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11755","citing_title":"Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03305","citing_title":"HVG-3D: Bridging Real and Simulation Domains for 3D-Conditional Hand-Object Interaction Video Synthesis","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":219,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7","json":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7.json","graph_json":"https://pith.science/api/pith-number/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/graph.json","events_json":"https://pith.science/api/pith-number/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/events.json","paper":"https://pith.science/paper/Z4TYGHSZ"},"agent_actions":{"view_html":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7","download_json":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7.json","view_paper":"https://pith.science/paper/Z4TYGHSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16863&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/action/storage_attestation","attest_author":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/action/author_attestation","sign_citation":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/action/citation_signature","submit_replication":"https://pith.science/pith/Z4TYGHSZR4NNLFLNDU2UNY5EZ7/action/replication_record"}},"created_at":"2026-07-05T08:36:04.716247+00:00","updated_at":"2026-07-05T08:36:04.716247+00:00"}