Pith. sign in

REVIEW 5 cited by

TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2306.08637 v2 pith:FMQBHMKU submitted 2023-06-14 cs.CV

TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement

classification cs.CV
keywords pointmodelqueryrefinementstagetrackingtrajectoriesvideo
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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. Our model facilitates fast inference on long and high-resolution video sequences. On a modern GPU, our implementation has the capacity to track points faster than real-time, and can be flexibly extended to higher-resolution videos. Given the high-quality trajectories extracted from a large dataset, we demonstrate a proof-of-concept diffusion model which generates trajectories from static images, enabling plausible animations. Visualizations, source code, and pretrained models can be found on our project webpage.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Human Universal Grasping

    cs.RO 2026-06 unverdicted novelty 7.0

    HUG trains a flow-matching model on a new 1M-frame egocentric human grasp dataset to generate retargetable grasps from single RGB-D images, beating baselines by 23-34% on a new 90-object benchmark.

  2. Causally Debiased Latent Action Model for Embodied Action Conditioned World Models

    cs.CV 2026-07 conditional novelty 6.0

    Three lightweight LAM fine-tuning objectives (foreground-weighted reconstruction, primitive contrastive learning, zero-transition calibration) debias latent actions and yield stronger, cheaper robot-action following i...

  3. MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction

    cs.CV 2026-06 unverdicted novelty 6.0

    Introduces a new task of goal-conditioned 3D point motion forecasting along with a 1.16M-video dataset, a 111-category benchmark, and a model that outperforms baselines while transferring to robotics and video generation.

  4. Turning Video Models into Generalist Robot Policies

    cs.RO 2026-05 unverdicted novelty 6.0

    Decouples action-free video world models from embodiment-specific IDMs using Jacobian-based translation to achieve zero-shot cross-embodiment robot policies.

  5. Intuitive Surgical SurgToolLoc and SurgVU Challenges Results: 2022-2025

    cs.CV 2023-05 unverdicted novelty 2.0

    The paper summarizes results from the SurgToolLoc and SurgVU challenges held at MICCAI conferences from 2022 to 2025.