Most state-of-the-art point trackers are trained on synthetic data due to the difficulty of
annotating real videos for this task. However, this can result in suboptimal performance due …

In this paper, we present TAPTRv2, a Transformer-based approach built upon TAPTR for
solving the Tracking Any Point (TAP) task. TAPTR borrows designs from DEtection …

This work aims to address an advanced keypoint detection problem: how to accurately
detect any keypoints in complex real-world scenarios, which involves massive, messy, and …

While recent foundational video generators produce visually rich output, they still struggle
with appearance drift, where objects gradually degrade or change inconsistently across …

Tracking dense 3D motion from monocular videos remains challenging, particularly when
aiming for pixel-level precision over long sequences. We introduce\Approach, a novel …

In this paper, we present TAPTRv3, which is built upon TAPTRv2 to improve its point
tracking robustness in long videos. TAPTRv2 is a simple DETR-like framework that can …

In this work, we present MFTIQ, a novel dense long-term tracking model that advances the
Multi-Flow Tracker (MFT) framework to address challenges in point-level visual tracking in …

In this paper, we study the problem of 3D reconstruction from a single-view RGB image and
propose a novel approach called DIG3D for 3D object reconstruction and novel view …

In this work, we present UniG, a view-consistent 3D reconstruction and novel view synthesis
model that generates a high-fidelity representation of 3D Gaussians from sparse images …

This report introduces an improved method for the Tracking Any Point~(TAP), focusing on
monitoring physical surfaces in video footage. Despite their success with short-sequence …