paper-with-me

Papers

KV-Tracker: Real-Time Pose Tracking with Transformers

2025-12-27 · Marwan Taher, Ignacio Alzugaray, Kirill Mazur, Xin Kong, Andrew J. Davison arxiv

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.

📄 PDF Abstract BibTeX arXiv:2512.22581

Code (0)

등록된 구현이 없습니다.

Tasks

Object TrackingPose Tracking

Similar Papers 제목 키워드 기반

Efficient Visual Tracking with Exemplar Transformers

2021-12-17 · Philippe Blatter, Menelaos Kanakis, Martin Danelljan, Luc van Gool

The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new bui…

CPUObject TrackingVideo Object TrackingVisual Object Tracking+1

Mobile Vision Transformer-based Visual Object Tracking

2023-09-11 · Goutam Yelluru Gopal, Maria A. Amer

The introduction of robust backbones, such as Vision Transformers, has improved the performance of object tracking algorithms in recent years. However, these state-of-the-art trackers are computationally expensive since …

GPUObjectObject TrackingVisual Object Tracking

Separable Self and Mixed Attention Transformers for Efficient Object Tracking

2023-09-07 · Goutam Yelluru Gopal, Maria A. Amer

The deployment of transformers for visual object tracking has shown state-of-the-art results on several benchmarks. However, the transformer-based models are under-utilized for Siamese lightweight tracking due to the com…

CPUGPUObject TrackingState Estimation+1

Lightweight RGB-T Tracking with Mobile Vision Transformers

2025-06-23 · Mahdi Falaki, Maria A. Amer

Single-modality object tracking (e.g., RGB-only) encounters difficulties in challenging imaging conditions, such as low illumination and adverse weather conditions. To solve this, multimodal tracking (e.g., RGB-T models)…

GPUObject TrackingRgb-T Tracking

On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?

2022-11-24 · Saksham Aggarwal, Taneesh Gupta, Pawan Kumar Sahu, Arnav Chavan 외

Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy backbones built using CNNs or transformers. Large sizes of s…

Network PruningObjectObject Tracking