TAPNext++: What's Next for Tracking Any Point (TAP)?

• URL: http://arxiv.org/abs/2604.10582v1
• Date: Sun, 12 Apr 2026 11:02:13 GMT
• Title: TAPNext++: What's Next for Tracking Any Point (TAP)?
• Abstract summary: We present a model that tracks points in sequences that are orders of magnitude longer while preserving the low memory and compute footprint of the architecture.<n>We highlight that re-detection performance is a blind spot in the current literature and introduce a new metric, Re-Detection Average Jaccard.<n>We demonstrate that recurrent transformers can be substantially improved for point tracking and set a new state-of-the-art on multiple benchmarks.
• Score: 58.6925880906723
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tracking-Any-Point (TAP) models aim to track any point through a video which is a crucial task in AR/XR and robotics applications. The recently introduced TAPNext approach proposes an end-to-end, recurrent transformer architecture to track points frame-by-frame in a purely online fashion -- demonstrating competitive performance at minimal latency. However, we show that TAPNext struggles with longer video sequences and also frequently fails to re-detect query points that reappear after being occluded or leaving the frame. In this work, we present TAPNext++, a model that tracks points in sequences that are orders of magnitude longer while preserving the low memory and compute footprint of the architecture. We train the recurrent video transformer using several data-driven solutions, including training on long 1024-frame sequences enabled by sequence parallelism techniques. We highlight that re-detection performance is a blind spot in the current literature and introduce a new metric, Re-Detection Average Jaccard ($AJ_{RD}$), to explicitly evaluate tracking on re-appearing points. To improve re-detection of points, we introduce tailored geometric augmentations, such as periodic roll that simulates point re-entries, and supervising occluded points. We demonstrate that recurrent transformers can be substantially improved for point tracking and set a new state-of-the-art on multiple benchmarks. Model and code can be found at https://tap-next-plus-plus.github.io.

Related papers

• TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views [50.26507994908593]
  We introduce TAPVid-MV (Tracking Any Point in Video across Multiple Views), the first benchmark for this setting.<n>It contains a curated set of 284 sequences, 1,142 calibrated camera streams, and 109,769 point tracks across seven subsets spanning indoor and outdoor domains.<n>We obtain these trajectories using dataset-specific auxiliary modalities: sensor depth, LiDAR, SLAM and SfM points, human meshes, posed object meshes, and simulation. Every sequence and trajectory is visually verified by human annotators.
  arXiv  Detail & Related papers  (2026-09-01T21:58:51Z)
• Generative Point Tracking with Flow Matching [32.15342097497571]
  We introduce Generative Point Tracker (GenPT), a generative framework for modelling multi-modal trajectories.<n>GenPT is trained with a novel flow matching formulation that combines the iterative refinement of discriminative trackers.<n>We show how our model's generative capabilities can be leveraged to improve point trajectory estimates.
  arXiv  Detail & Related papers  (2025-10-23T19:25:14Z)
• Track-On: Transformer-based Online Point Tracking with Memory [34.744546679670734]
  We introduce Track-On, a simple transformer-based model designed for online long-term point tracking.<n>Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames.<n>At inference time, it employs patch classification and refinement to identify correspondences and track points with high accuracy.
  arXiv  Detail & Related papers  (2025-01-30T17:04:11Z)
• Solution for Point Tracking Task of ECCV 2nd Perception Test Challenge 2024 [13.14886222358538]
  This report introduces an improved method for the Tracking Any Point(TAP), focusing on monitoring physical surfaces in video footage. We propose a simple yet effective approach called Fine-grained Point Discrimination(textbfFPD), which focuses on perceiving and rectifying point tracking at multiple granularities in zero-shot manner.
  arXiv  Detail & Related papers  (2024-10-05T15:09:40Z)
• Robust Visual Tracking via Iterative Gradient Descent and Threshold Selection [4.978166837959101]
  We introduce a novel robust linear regression estimator, which achieves favorable performance when the error vector follows i.i.d Gaussian-Laplacian distribution. In addition, we expend IGDTS to a generative tracker, and apply IGDTS-distance to measure the deviation between the sample and the model. Experimental results on several challenging image sequences show that the proposed tracker outperformance existing trackers.
  arXiv  Detail & Related papers  (2024-06-02T01:51:09Z)
• CoTracker: It is Better to Track Together [70.63040730154984]
  CoTracker is a transformer-based model that tracks a large number of 2D points in long video sequences. We show that joint tracking significantly improves tracking accuracy and robustness, and allows CoTracker to track occluded points and points outside of the camera view.
  arXiv  Detail & Related papers  (2023-07-14T21:13:04Z)
• TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement [64.11385310305612]
  We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence. Our approach employs two stages: (1) a matching stage, which independently locates a suitable candidate point match for the query point on every other frame, and (2) a refinement stage, which updates both the trajectory and query features based on local correlations. The resulting model surpasses all baseline methods by a significant margin on the TAP-Vid benchmark, as demonstrated by an approximate 20% absolute average Jaccard (AJ) improvement on DAVIS.
  arXiv  Detail & Related papers  (2023-06-14T17:07:51Z)
• Unified Sequence-to-Sequence Learning for Single- and Multi-Modal Visual Object Tracking [64.28025685503376]
  SeqTrack casts visual tracking as a sequence generation task, forecasting object bounding boxes in an autoregressive manner. SeqTrackv2 integrates a unified interface for auxiliary modalities and a set of task-prompt tokens to specify the task. This sequence learning paradigm not only simplifies the tracking framework, but also showcases superior performance across 14 challenging benchmarks.
  arXiv  Detail & Related papers  (2023-04-27T17:56:29Z)
• Tracking by Associating Clips [110.08925274049409]
  In this paper, we investigate an alternative by treating object association as clip-wise matching. Our new perspective views a single long video sequence as multiple short clips, and then the tracking is performed both within and between the clips. The benefits of this new approach are two folds. First, our method is robust to tracking error accumulation or propagation, as the video chunking allows bypassing the interrupted frames. Second, the multiple frame information is aggregated during the clip-wise matching, resulting in a more accurate long-range track association than the current frame-wise matching.
  arXiv  Detail & Related papers  (2022-12-20T10:33:17Z)
• TAP-Vid: A Benchmark for Tracking Any Point in a Video [84.94877216665793]
  We formalize the problem of tracking arbitrary physical points on surfaces over longer video clips, naming it tracking any point (TAP) We introduce a companion benchmark, TAP-Vid, which is composed of both real-world videos with accurate human annotations of point tracks, and synthetic videos with perfect ground-truth point tracks. We propose a simple end-to-end point tracking model TAP-Net, showing that it outperforms all prior methods on our benchmark when trained on synthetic data.
  arXiv  Detail & Related papers  (2022-11-07T17:57:02Z)
• REGTR: End-to-end Point Cloud Correspondences with Transformers [79.52112840465558]
  We conjecture that attention mechanisms can replace the role of explicit feature matching and RANSAC. We propose an end-to-end framework to directly predict the final set of correspondences. Our approach achieves state-of-the-art performance on 3DMatch and ModelNet benchmarks.
  arXiv  Detail & Related papers  (2022-03-28T06:01:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.