Point Tracking

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

8 leaderboard tables shown for this task, 8 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 61 papers with code (151 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold
  18 May 2023 7 repositories listed Syntology ran 7 of 16 samples · 9 unverified · 3 pointer-only (licence)
  Synthesizing visual content that meets users' needs often requires flexible and precise controllability of the pose, shape, expression, and layout of the generated objects.
• PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking
  27 Jul 2023 3 repositories listed Syntology ran 10 of 13 samples · 3 unverified · 8 pointer-only (licence)
  Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion.
• TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
  14 Jun 2023 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence.
• TAP-Vid: A Benchmark for Tracking Any Point in a Video
  7 Nov 2022 3 repositories listed Syntology ran 4 of 12 samples · 8 unverified · 2 pointer-only (licence)
  Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move.
• Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos
  23 Jul 2024 2 repositories listed Syntology ran 20 of 23 samples · 3 unverified
  Despite the impressive progress, research on metrics for evaluating the quality of generated videos, especially concerning temporal and motion consistency, remains underexplored.
• Local All-Pair Correspondence for Point Tracking
  22 Jul 2024 2 repositories listed Syntology ran 6 of 12 samples · 6 unverified
  We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences.
• TAPVid-3D: A Benchmark for Tracking Any Point in 3D
  8 Jul 2024 2 repositories listed
  We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D).
• BootsTAP: Bootstrapped Training for Tracking-Any-Point
  1 Feb 2024 2 repositories listed
  To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes.
• CoTracker: It is Better to Track Together
  14 Jul 2023 2 repositories listed
  We introduce CoTracker, a transformer-based model that tracks a large number of 2D points in long video sequences.
• SpatialTrackerV2: 3D Point Tracking Made Easy
  16 Jul 2025 1 repository listed
  We present SpatialTrackerV2, a feed-forward 3D point tracking method for monocular videos.
• CharaConsist: Fine-Grained Consistent Character Generation
  15 Jul 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In text-to-image generation, producing a series of consistent contents that preserve the same identity is highly valuable for real-world applications.
• DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
  18 May 2025 1 repository listed
  Drag-based editing within pretrained diffusion model provides a precise and flexible way to manipulate foreground objects.
• TAPIP3D: Tracking Any Point in Persistent 3D Geometry
  20 Apr 2025 1 repository listed Syntology ran 2 of 8 samples · 6 unverified
  We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos.
• Seurat: From Moving Points to Depth
  20 Apr 2025 1 repository listed
  Accurate depth estimation from monocular videos remains challenging due to ambiguities inherent in single-view geometry, as crucial depth cues like stereopsis are absent.
• POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
  8 Apr 2025 1 repository listed Syntology ran 5 of 6 samples · 1 unverified · 6 pointer-only (licence)
  Furthermore, we introduce a temporal motion module for dynamic motions that ensures scale consistency across different frames and enhances performance in tasks requiring both precise geometry and reliable matching, most…
• TAPNext: Tracking Any Point (TAP) as Next Token Prediction
  8 Apr 2025 1 repository listed
  Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction.
• Point Tracking in Surgery--The 2024 Surgical Tattoos in Infrared (STIR) Challenge
  31 Mar 2025 1 repository listed
  Understanding tissue motion in surgery is crucial to enable applications in downstream tasks such as segmentation, 3D reconstruction, virtual tissue landmarking, autonomous probe-based scanning, and subtask autonomy.
• VGGT: Visual Geometry Grounded Transformer
  14 Mar 2025 1 repository listed
  We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views.
• Low Complexity Point Tracking of the Myocardium in 2D Echocardiography
  13 Mar 2025 1 repository listed
  The limits of agreement were wider for both CoTracker2 and EchoTracker, worse than the interobserver variability.
• Online Dense Point Tracking with Streaming Memory
  9 Mar 2025 1 repository listed Syntology ran 5 of 12 samples · 7 unverified
  Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video, even in the presence of occlusions.
• Track-On: Transformer-based Online Point Tracking with Memory
  30 Jan 2025 1 repository listed Syntology ran 0 of 2 samples · 2 unverified
  In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and…
• Exploring Temporally-Aware Features for Point Tracking
  21 Jan 2025 1 repository listed
  Point tracking in videos is a fundamental task with applications in robotics, video editing, and more.
• MATCHA: Towards Matching Anything
  1 Jan 2025 1 repository listed
  Inspired by this flexibility, we propose MATCHA, a unified feature model designed to "rule them all", establishing robust correspondences across diverse matching tasks.
• CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
  15 Oct 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Most state-of-the-art point trackers are trained on synthetic data due to the difficulty of annotating real videos for this task.
• Self-Supervised Any-Point Tracking by Contrastive Random Walks
  24 Sep 2024 1 repository listed Syntology ran 4 of 8 samples · 4 unverified
  We present a simple, self-supervised approach to the Tracking Any Point (TAP) problem.
• Foundation Models for Amodal Video Instance Segmentation in Automated Driving
  21 Sep 2024 1 repository listed
  This way, while basing our method on an amodal instance segmentation, we nevertheless obtain video-level amodal instance segmentation results.
• Leveraging Object Priors for Point Tracking
  9 Sep 2024 1 repository listed
  Point tracking is a fundamental problem in computer vision with numerous applications in AR and robotics.
• A Training-Free Framework for Video License Plate Tracking and Recognition with Only One-Shot
  11 Aug 2024 1 repository listed
  We propose OneShotLP, a training-free framework for video-based license plate detection and recognition, leveraging these advanced models.
• Autogenic Language Embedding for Coherent Point Tracking
  30 Jul 2024 1 repository listed
  Point tracking is a challenging task in computer vision, aiming to establish point-wise correspondence across long video sequences.
• Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation
  15 Jul 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  In optical flow estimation, our method elevates a simple UNet to achieve state-of-the-art performance among self-supervised methods on the DSEC optical flow benchmark.

Syntology lines on 14 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.