LiteTracker: Leveraging Temporal Causality for Accurate Low-latency Tissue Tracking

2025-04-14

AI Summary

High-precision tissue tracking methods exhibit strong generalization but incur prohibitive computational overhead, hindering real-time performance required for surgical navigation and extended reality (XR) applications. To address this, we propose a runtime optimization framework that requires no retraining: it introduces a novel temporal memory caching mechanism to enable cross-frame feature reuse, and incorporates motion priors to guide trajectory initialization. Built upon long-term point tracking, our approach integrates temporal causal modeling with online inter-frame feature caching. Evaluated on the STIR and SuPer benchmarks, our method achieves approximately 7× speedup over prior work and 2× acceleration over the state-of-the-art, while maintaining high tracking accuracy and robustness to occlusions. Notably, it is the first method to achieve clinically viable real-time performance—defined as sub-33-ms latency—without compromising tracking precision.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Tissue tracking plays a critical role in various surgical navigation and extended reality (XR) applications. While current methods trained on large synthetic datasets achieve high tracking accuracy and generalize well to endoscopic scenes, their runtime performances fail to meet the low-latency requirements necessary for real-time surgical applications. To address this limitation, we propose LiteTracker, a low-latency method for tissue tracking in endoscopic video streams. LiteTracker builds on a state-of-the-art long-term point tracking method, and introduces a set of training-free runtime optimizations. These optimizations enable online, frame-by-frame tracking by leveraging a temporal memory buffer for efficient feature reuse and utilizing prior motion for accurate track initialization. LiteTracker demonstrates significant runtime improvements being around 7x faster than its predecessor and 2x than the state-of-the-art. Beyond its primary focus on efficiency, LiteTracker delivers high-accuracy tracking and occlusion prediction, performing competitively on both the STIR and SuPer datasets. We believe LiteTracker is an important step toward low-latency tissue tracking for real-time surgical applications in the operating room.

Problem

• Achieving low-latency tissue tracking for real-time surgery
• Improving runtime performance without sacrificing tracking accuracy
• Enabling efficient feature reuse and track initialization in endoscopy

Innovation

• Leverages temporal memory buffer for feature reuse
• Utilizes prior motion for track initialization
• Achieves 7x speedup over predecessor methods