KV-Tracker: Real-Time Pose Tracking with Transformers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Taher, Marwan, Alzugaray, Ignacio, Mazur, Kirill, Kong, Xin, Davison, Andrew J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909976855838720
author Taher, Marwan
Alzugaray, Ignacio
Mazur, Kirill
Kong, Xin
Davison, Andrew J.
author_facet Taher, Marwan
Alzugaray, Ignacio
Mazur, Kirill
Kong, Xin
Davison, Andrew J.
contents Multi-view 3D geometry networks offer a powerful prior but are prohibitively slow for real-time applications. We propose a novel way to adapt them for online use, enabling real-time 6-DoF pose tracking and online reconstruction of objects and scenes from monocular RGB videos. Our method rapidly selects and manages a set of images as keyframes to map a scene or object via $π^3$ with full bidirectional attention. We then cache the global self-attention block's key-value (KV) pairs and use them as the sole scene representation for online tracking. This allows for up to $15\times$ speedup during inference without the fear of drift or catastrophic forgetting. Our caching strategy is model-agnostic and can be applied to other off-the-shelf multi-view networks without retraining. We demonstrate KV-Tracker on both scene-level tracking and the more challenging task of on-the-fly object tracking and reconstruction without depth measurements or object priors. Experiments on the TUM RGB-D, 7-Scenes, Arctic and OnePose datasets show the strong performance of our system while maintaining high frame-rates up to ${\sim}27$ FPS.
format Preprint
id arxiv_https___arxiv_org_abs_2512_22581
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KV-Tracker: Real-Time Pose Tracking with Transformers
Taher, Marwan
Alzugaray, Ignacio
Mazur, Kirill
Kong, Xin
Davison, Andrew J.
Computer Vision and Pattern Recognition
Multi-view 3D geometry networks offer a powerful prior but are prohibitively slow for real-time applications. We propose a novel way to adapt them for online use, enabling real-time 6-DoF pose tracking and online reconstruction of objects and scenes from monocular RGB videos. Our method rapidly selects and manages a set of images as keyframes to map a scene or object via $π^3$ with full bidirectional attention. We then cache the global self-attention block's key-value (KV) pairs and use them as the sole scene representation for online tracking. This allows for up to $15\times$ speedup during inference without the fear of drift or catastrophic forgetting. Our caching strategy is model-agnostic and can be applied to other off-the-shelf multi-view networks without retraining. We demonstrate KV-Tracker on both scene-level tracking and the more challenging task of on-the-fly object tracking and reconstruction without depth measurements or object priors. Experiments on the TUM RGB-D, 7-Scenes, Arctic and OnePose datasets show the strong performance of our system while maintaining high frame-rates up to ${\sim}27$ FPS.
title KV-Tracker: Real-Time Pose Tracking with Transformers
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.22581