KV-Tracker: Real-Time Pose Tracking with Transformers

TL;DR

KV-Tracker enables real-time 6-DoF pose tracking and scene reconstruction from monocular RGB videos by caching global self-attention key-value pairs, achieving significant speedups without sacrificing accuracy.

Contribution

It introduces a novel caching strategy for multi-view networks that allows real-time pose tracking and reconstruction without retraining or depth data.

Findings

Achieves up to 27 FPS in experiments.

Maintains accuracy without drift or forgetting.

Applicable to various multi-view networks.

Abstract

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 $\pi^3$ 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.