{"id":"4888ee4c-71f5-4e69-8b49-030297ec0c16","slug":"trackeverything","name":"TrackEverything","description":"TrackEverything is a Sep 2026 academic 3D point tracker (Jain, Paruchuri, Gupta, Zhang, Schmidt, Engel, Fragkiadaki, Harley; arXiv 2609.30222) that represents videos as persistent 3D scene tracks in world coordinates. Voxel de-duplication at sliding-window boundaries merges co-located tracks so memory scales with unique scene geometry rather than clip length; 3D WAFT samples features in the scene cloud instead of building 4D correlation volumes. Research demo for long-horizon dense tracking / robotics / spatial / 4D reconstruction; not a commercial product.","brainType":"research-model","isOpen":false,"maturityStage":"research","architecture":"Persistent 3D scene tracks in world coordinates; voxelization-based de-duplication at sliding-window boundaries; endpoint refiner with static-vs-dynamic classification; lightweight trajectory refiner for dynamic points; 3D WAFT feature sampling in the scene cloud","reviewStatus":"reviewed","sources":[{"url":"https://arxiv.org/abs/2609.30222","title":"TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations (arXiv:2609.30222)","sourceName":"arXiv","publishedAt":"2026-09-30"},{"url":"https://arxiv.org/pdf/2609.30222","title":"TrackEverything PDF (arXiv:2609.30222)","sourceName":"arXiv","publishedAt":"2026-09-30"},{"url":"https://x.com/robotsdigest/status/2105304160451056084","title":"Secondary summary: TrackEverything voxel de-duplication (robotsdigest)","sourceName":"X (@robotsdigest)","publishedAt":"2026-09-30"}],"keyFacts":[{"label":"System (project-stated)","value":"Project-stated (project-stated): TrackEverything (Jain / Paruchuri / Gupta / Zhang / Schmidt / Engel / Fragkiadaki / Harley; arXiv 2609.30222) is a 3D point tracker that represents videos as persistent 3D scene tracks in world coordinates so complexity scales with unique scene geometry rather than video length. Academic research system, not a commercial product"},{"label":"Voxel de-duplication + 3D WAFT (project-stated)","value":"Project-stated (project-stated): voxelization-based de-duplication at sliding-window boundaries merges co-located tracks; tracking decomposes into endpoint refinement plus static-vs-dynamic classification and a lightweight trajectory refiner for dynamic points; 3D WAFT replaces memory-heavy 4D correlation volumes with feature sampling in the scene cloud. Cap: paper-reported method"},{"label":"TAPVid-3D dense-tracking margin","value":"The paper reports that on TAPVid-3D, TrackEverything outperforms open-source all-frame dense 3D trackers by more than 20% APD on short clips while tracking all visible points (arXiv 2609.30222)."},{"label":"Long-horizon memory bound","value":"The authors say TrackEverything is, to their knowledge, the first 3D tracker that can track all visible points across videos longer than 1000 frames within 40 GB of GPU memory (arXiv 2609.30222)."},{"label":"CMU and Meta authors","value":"The paper lists authors affiliated with Carnegie Mellon University and Meta and points to the project site trackeverything.github.io (arXiv 2609.30222)."}],"aliases":["TrackEverything","Track Everything","Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"],"collisionRisk":"low","reviewNote":null,"builtOnBrainId":null,"createdAt":"2026-09-30T15:56:20.004Z","updatedAt":"2026-10-09T22:00:38.966Z","jsonLd":{"@context":"https://schema.org","@type":"SoftwareApplication","@id":"https://registry.deploy.report/brains/trackeverything","url":"https://registry.deploy.report/brains/trackeverything","name":"TrackEverything","alternateName":["TrackEverything","Track Everything","Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations"],"description":"TrackEverything is a Sep 2026 academic 3D point tracker (Jain, Paruchuri, Gupta, Zhang, Schmidt, Engel, Fragkiadaki, Harley; arXiv 2609.30222) that represents videos as persistent 3D scene tracks in world coordinates. Voxel de-duplication at sliding-window boundaries merges co-located tracks so memory scales with unique scene geometry rather than clip length; 3D WAFT samples features in the scene cloud instead of building 4D correlation volumes. Research demo for long-horizon dense tracking / robotics / spatial / 4D reconstruction; not a commercial product.","identifier":"4888ee4c-71f5-4e69-8b49-030297ec0c16","applicationCategory":"research-model","publisher":{"@id":"https://deploy.report/#organization"}},"framework_metadata":{"framework_schema_version":"0.1.0","verification_status":"verified","maturity_stage":"research","lifecycle_state":null,"architectural_position":{"cohort":null,"sub_cohorts":[]},"within_cohort_verified_vs_claimed_pair":null,"cap_flags":[],"verification_depth":{"sources_count":3,"primary_source_types":["preprint"]}}}