{"paper":{"title":"TrajectoryMover: Generative Movement of Object Trajectories in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A new video generator uses synthetic paired data to move objects along altered 3D trajectories while keeping their original motion intact.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christopher E. Peters, Chun-Hao Paul Huang, Hyeonho Jeong, Kiran Chhatre, Paul Guerrero, Yulia Gryaditskaya","submitted_at":"2026-03-31T00:15:36Z","abstract_excerpt":"Generative video editing has enabled several intuitive editing operations for short video clips that would previously have been difficult to achieve, especially for non-expert editors. Existing methods focus on prescribing an object's 3D or 2D motion trajectory in a video, or on altering the appearance of an object or a scene, while preserving both the video's plausibility and identity. Yet a method to move an object's 3D motion trajectory in a video, i.e., moving an object while preserving its relative 3D motion, is currently still missing. The main challenge lies in obtaining paired video da"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce TrajectoryAtlas, a new data generation pipeline for large-scale synthetic paired video data and a video generator TrajectoryMover fine-tuned with this data. We show that this successfully enables generative movement of object trajectories.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic paired videos produced by TrajectoryAtlas are sufficiently realistic and diverse to allow the fine-tuned TrajectoryMover to generalize to real-world videos without introducing artifacts or breaking motion plausibility.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TrajectoryMover enables moving object trajectories in videos by training on large-scale synthetic paired data generated via the new TrajectoryAtlas pipeline.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new video generator uses synthetic paired data to move objects along altered 3D trajectories while keeping their original motion intact.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cbda9d4f1fe4fad95a99d08243efece39db5b968a90b4e412881b05ebc981c07"},"source":{"id":"2603.29092","kind":"arxiv","version":3},"verdict":{"id":"392af153-8dce-47a8-a1ab-22b4a6cecf82","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T00:15:50.530988Z","strongest_claim":"We introduce TrajectoryAtlas, a new data generation pipeline for large-scale synthetic paired video data and a video generator TrajectoryMover fine-tuned with this data. We show that this successfully enables generative movement of object trajectories.","one_line_summary":"TrajectoryMover enables moving object trajectories in videos by training on large-scale synthetic paired data generated via the new TrajectoryAtlas pipeline.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic paired videos produced by TrajectoryAtlas are sufficiently realistic and diverse to allow the fine-tuned TrajectoryMover to generalize to real-world videos without introducing artifacts or breaking motion plausibility.","pith_extraction_headline":"A new video generator uses synthetic paired data to move objects along altered 3D trajectories while keeping their original motion intact."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.29092/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"}