Deep learning methods for point tracking are applicable in 2D echocardiography, but do not yet take advantage of domain specifics that enable extremely fast and efficient configurations. We developed MyoTracker, a low-complexity architecture (0.3M parameters) for point tracking in echocardiography. It builds on the CoTracker2 architecture by simplifying its components and extending the temporal context to provide point predictions for the entire sequence in a single step. We applied MyoTracker to the right ventricular (RV) myocardium in RV-focused recordings and compared the results with those of CoTracker2 and EchoTracker, another specialized point tracking architecture for echocardiography. MyoTracker achieved the lowest average point trajectory error at 2.00 $\pm$ 0.53 mm. Calculating RV Free Wall Strain (RV FWS) using MyoTracker's point predictions resulted in a -0.3$\%$ bias with 95$\%$ limits of agreement from -6.1$\%$ to 5.4$\%$ compared to reference values from commercial software. This range falls within the interobserver variability reported in previous studies. The limits of agreement were wider for both CoTracker2 and EchoTracker, worse than the interobserver variability. At inference, MyoTracker used 67$\%$ less GPU memory than CoTracker2 and 84$\%$ less than EchoTracker on large sequences (100 frames). MyoTracker was 74 times faster during inference than CoTracker2 and 11 times faster than EchoTracker with our setup. Maintaining the entire sequence in the temporal context was the greatest contributor to MyoTracker's accuracy. Slight additional gains can be made by re-enabling iterative refinement, at the cost of longer processing time.
Dense point tracking is a challenging task requiring the continuous tracking of every point in the initial frame throughout a substantial portion of a video, even in the presence of occlusions. Traditional methods use optical flow models to directly estimate long-range motion, but they often suffer from appearance drifting without considering temporal consistency. Recent point tracking algorithms usually depend on sliding windows for indirect information propagation from the first frame to the current one, which is slow and less effective for long-range tracking. To account for temporal consistency and enable efficient information propagation, we present a lightweight and fast model with \textbf{S}treaming memory for dense \textbf{PO}int \textbf{T}racking and online video processing. The \textbf{SPOT} framework features three core components: a customized memory reading module for feature enhancement, a sensory memory for short-term motion dynamics modeling, and a visibility-guided splatting module for accurate information propagation. This combination enables SPOT to perform dense point tracking with state-of-the-art accuracy on the CVO benchmark, as well as comparable or superior performance to offline models on sparse tracking benchmarks such as TAP-Vid and RoboTAP. Notably, SPOT with 10$\times$ smaller parameter numbers operates at least 2$\times$ faster than previous state-of-the-art models while maintaining the best performance on CVO. We will release the models and codes at: https://github.com/DQiaole/SPOT.
Many everyday mobile manipulation tasks require precise interaction with small objects, such as grasping a knob to open a cabinet or pressing a light switch. In this paper, we develop Servoing with Vision Models (SVM), a closed-loop training-free framework that enables a mobile manipulator to tackle such precise tasks involving the manipulation of small objects. SVM employs an RGB-D wrist camera and uses visual servoing for control. Our novelty lies in the use of state-of-the-art vision models to reliably compute 3D targets from the wrist image for diverse tasks and under occlusion due to the end-effector. To mitigate occlusion artifacts, we employ vision models to out-paint the end-effector thereby significantly enhancing target localization. We demonstrate that aided by out-painting methods, open-vocabulary object detectors can serve as a drop-in module to identify semantic targets (e.g. knobs) and point tracking methods can reliably track interaction sites indicated by user clicks. This training-free method obtains an 85% zero-shot success rate on manipulating unseen objects in novel environments in the real world, outperforming an open-loop control method and an imitation learning baseline trained on 1000+ demonstrations by an absolute success rate of 50%.
Foundation models pre-trained on massive unlabeled datasets have revolutionized natural language and computer vision, exhibiting remarkable generalization capabilities, thus highlighting the importance of pre-training. Yet, efforts in robotics have struggled to achieve similar success, limited by either the need for costly robotic annotations or the lack of representations that effectively model the physical world. In this paper, we introduce ARM4R, an Auto-regressive Robotic Model that leverages low-level 4D Representations learned from human video data to yield a better pre-trained robotic model. Specifically, we focus on utilizing 3D point tracking representations from videos derived by lifting 2D representations into 3D space via monocular depth estimation across time. These 4D representations maintain a shared geometric structure between the points and robot state representations up to a linear transformation, enabling efficient transfer learning from human video data to low-level robotic control. Our experiments show that ARM4R can transfer efficiently from human video data to robotics and consistently improves performance on tasks across various robot environments and configurations.
Consider an unmanned aerial vehicle (UAV) physically connected to the ground station with a tether operating in a space, tasked with performing precise maneuvers while constrained by the physical limitation of its tether, which prevents it from flying beyond a maximum allowable length. Violating this tether constraint could lead to system failure or operational hazards, making it essential to enforce safety constraints dynamically while ensuring the drone can track desired trajectories accurately. This paper presents a Control Barrier Function Quadratic Programming Framework (CBF-QP) for ensuring the safe and efficient operation of tethered unmanned aerial vehicles (TUAVs). The framework leverages nominal backstepping control to achieve trajectory tracking, augmented with control barrier functions to ensure compliance with the tether constraint. In this proposed method, the tether constraint is directly embedded in the control design and therefore guarantees the TUAV remains within a predefined operational region defined by the maximum tether length while achieving precise trajectory tracking. The effectiveness of the proposed framework is validated through simulations involving set-point tracking, dynamic trajectory following, and disturbances such as incorrect user inputs. The results demonstrate that the TUAV respects the tether constraint ||x(t)||</= Lmax, with tracking errors converging to zero and the control input remaining bounded.
In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online tracking on a frame-by-frame basis, making it suitable for real-world, streaming scenarios. Specifically, we introduce Track-On, a simple transformer-based model designed for online long-term point tracking. Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames, leveraging two memory modules -- spatial memory and context memory -- to capture temporal information and maintain reliable point tracking over long time horizons. At inference time, it employs patch classification and refinement to identify correspondences and track points with high accuracy. Through extensive experiments, we demonstrate that Track-On sets a new state-of-the-art for online models and delivers superior or competitive results compared to offline approaches on seven datasets, including the TAP-Vid benchmark. Our method offers a robust and scalable solution for real-time tracking in diverse applications. Project page: https://kuis-ai.github.io/track_on
Establishing correspondences across images is a fundamental challenge in computer vision, underpinning tasks like Structure-from-Motion, image editing, and point tracking. Traditional methods are often specialized for specific correspondence types, geometric, semantic, or temporal, whereas humans naturally identify alignments across these domains. Inspired by this flexibility, we propose MATCHA, a unified feature model designed to ``rule them all'', establishing robust correspondences across diverse matching tasks. Building on insights that diffusion model features can encode multiple correspondence types, MATCHA augments this capacity by dynamically fusing high-level semantic and low-level geometric features through an attention-based module, creating expressive, versatile, and robust features. Additionally, MATCHA integrates object-level features from DINOv2 to further boost generalization, enabling a single feature capable of matching anything. Extensive experiments validate that MATCHA consistently surpasses state-of-the-art methods across geometric, semantic, and temporal matching tasks, setting a new foundation for a unified approach for the fundamental correspondence problem in computer vision. To the best of our knowledge, MATCHA is the first approach that is able to effectively tackle diverse matching tasks with a single unified feature.
Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve generalizability, point tracking has primarily relied on simpler backbones trained from scratch on synthetic data, which may limit robustness in real-world scenarios. Additionally, point tracking requires temporal awareness to ensure coherence across frames, but using temporally-aware features is still underexplored. Most current methods often employ a two-stage process: an initial coarse prediction followed by a refinement stage to inject temporal information and correct errors from the coarse stage. These approach, however, is computationally expensive and potentially redundant if the feature backbone itself captures sufficient temporal information. In this work, we introduce Chrono, a feature backbone specifically designed for point tracking with built-in temporal awareness. Leveraging pre-trained representations from self-supervised learner DINOv2 and enhanced with a temporal adapter, Chrono effectively captures long-term temporal context, enabling precise prediction even without the refinement stage. Experimental results demonstrate that Chrono achieves state-of-the-art performance in a refiner-free setting on the TAP-Vid-DAVIS and TAP-Vid-Kinetics datasets, among common feature backbones used in point tracking as well as DINOv2, with exceptional efficiency. Project page: https://cvlab-kaist.github.io/Chrono/
4D video control is essential in video generation as it enables the use of sophisticated lens techniques, such as multi-camera shooting and dolly zoom, which are currently unsupported by existing methods. Training a video Diffusion Transformer (DiT) directly to control 4D content requires expensive multi-view videos. Inspired by Monocular Dynamic novel View Synthesis (MDVS) that optimizes a 4D representation and renders videos according to different 4D elements, such as camera pose and object motion editing, we bring pseudo 4D Gaussian fields to video generation. Specifically, we propose a novel framework that constructs a pseudo 4D Gaussian field with dense 3D point tracking and renders the Gaussian field for all video frames. Then we finetune a pretrained DiT to generate videos following the guidance of the rendered video, dubbed as GS-DiT. To boost the training of the GS-DiT, we also propose an efficient Dense 3D Point Tracking (D3D-PT) method for the pseudo 4D Gaussian field construction. Our D3D-PT outperforms SpatialTracker, the state-of-the-art sparse 3D point tracking method, in accuracy and accelerates the inference speed by two orders of magnitude. During the inference stage, GS-DiT can generate videos with the same dynamic content while adhering to different camera parameters, addressing a significant limitation of current video generation models. GS-DiT demonstrates strong generalization capabilities and extends the 4D controllability of Gaussian splatting to video generation beyond just camera poses. It supports advanced cinematic effects through the manipulation of the Gaussian field and camera intrinsics, making it a powerful tool for creative video production. Demos are available at https://wkbian.github.io/Projects/GS-DiT/.
In this paper, we propose ProTracker, a novel framework for robust and accurate long-term dense tracking of arbitrary points in videos. The key idea of our method is incorporating probabilistic integration to refine multiple predictions from both optical flow and semantic features for robust short-term and long-term tracking. Specifically, we integrate optical flow estimations in a probabilistic manner, producing smooth and accurate trajectories by maximizing the likelihood of each prediction. To effectively re-localize challenging points that disappear and reappear due to occlusion, we further incorporate long-term feature correspondence into our flow predictions for continuous trajectory generation. Extensive experiments show that ProTracker achieves the state-of-the-art performance among unsupervised and self-supervised approaches, and even outperforms supervised methods on several benchmarks. Our code and model will be publicly available upon publication.
Solar energy utilization in places like Nepal, is often obstructed by unpredicted environmental factors and existing technological barriers. The challenges encountered often result in fluctuating energy outputs, hindering the transition to greener energy solutions. To tackle these issues, this study introduces a custom-designed Maximum Power Point Tracking (MPPT) controller, seamlessly incorporated into a microcontroller-based battery charging system. This approach seeks to enhance the efficiency of photovoltaic (PV) systems, aligning with the global shift towards renewables. The research's primary objective is to enhance PV module power yield employing MPPT techniques, thereby reducing dependency on non-renewable energy sources. Key goals include real-time MPP tracking for optimal power extraction from PV modules and the integration of a real-time monitoring mechanism for PV and battery states. Leveraging a coordinated interplay of sensors measuring temperature, voltage, and current, vital metrics are fed to the microcontroller. This, in turn, generates a precise Pulse Width Modulation (PWM) signal, fine-tuning the voltage regulation of the buck-boost converter Metal Oxide Semiconductor Field Effect Transistor (MOSFET) for optimal operation. The adopted approach emphasizes monitoring environmental metrics, overseeing power outputs, and generating PWM signals to adeptly manage the buck-boost converter MOSFET voltage. Concurrently, data is transmitted hourly to a cloud platform, facilitating real-time monitoring capabilities showcasing the IoT application. As a result of these integrations, an efficiency improvement of approximately 37.28% was observed. In essence, this research underscores the profound impact of merging advanced technologies within the renewable energy sector, offering a robust blueprint for enhancing energy stability and productivity.
While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across frames, breaking visual coherence. We hypothesize that this is because there is no explicit supervision in terms of spatial tracking at the feature level. We propose Track4Gen, a spatially aware video generator that combines video diffusion loss with point tracking across frames, providing enhanced spatial supervision on the diffusion features. Track4Gen merges the video generation and point tracking tasks into a single network by making minimal changes to existing video generation architectures. Using Stable Video Diffusion as a backbone, Track4Gen demonstrates that it is possible to unify video generation and point tracking, which are typically handled as separate tasks. Our extensive evaluations show that Track4Gen effectively reduces appearance drift, resulting in temporally stable and visually coherent video generation. Project page: hyeonho99.github.io/track4gen
We introduce EgoPoints, a benchmark for point tracking in egocentric videos. We annotate 4.7K challenging tracks in egocentric sequences. Compared to the popular TAP-Vid-DAVIS evaluation benchmark, we include 9x more points that go out-of-view and 59x more points that require re-identification (ReID) after returning to view. To measure the performance of models on these challenging points, we introduce evaluation metrics that specifically monitor tracking performance on points in-view, out-of-view, and points that require re-identification. We then propose a pipeline to create semi-real sequences, with automatic ground truth. We generate 11K such sequences by combining dynamic Kubric objects with scene points from EPIC Fields. When fine-tuning point tracking methods on these sequences and evaluating on our annotated EgoPoints sequences, we improve CoTracker across all metrics, including the tracking accuracy $\delta^\star_{\text{avg}}$ by 2.7 percentage points and accuracy on ReID sequences (ReID$\delta_{\text{avg}}$) by 2.4 points. We also improve $\delta^\star_{\text{avg}}$ and ReID$\delta_{\text{avg}}$ of PIPs++ by 0.3 and 2.8 respectively.
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 accurately track any point in real-world videos without requiring cost-volume. TAPTRv3 improves TAPTRv2 by addressing its shortage in querying high quality features from long videos, where the target tracking points normally undergo increasing variation over time. In TAPTRv3, we propose to utilize both spatial and temporal context to bring better feature querying along the spatial and temporal dimensions for more robust tracking in long videos. For better spatial feature querying, we present Context-aware Cross-Attention (CCA), which leverages surrounding spatial context to enhance the quality of attention scores when querying image features. For better temporal feature querying, we introduce Visibility-aware Long-Temporal Attention (VLTA) to conduct temporal attention to all past frames while considering their corresponding visibilities, which effectively addresses the feature drifting problem in TAPTRv2 brought by its RNN-like long-temporal modeling. TAPTRv3 surpasses TAPTRv2 by a large margin on most of the challenging datasets and obtains state-of-the-art performance. Even when compared with methods trained with large-scale extra internal data, TAPTRv3 is still competitive.
Following the successful 2023 edition, we organised the Second Perception Test challenge as a half-day workshop alongside the IEEE/CVF European Conference on Computer Vision (ECCV) 2024, with the goal of benchmarking state-of-the-art video models and measuring the progress since last year using the Perception Test benchmark. This year, the challenge had seven tracks (up from six last year) and covered low-level and high-level tasks, with language and non-language interfaces, across video, audio, and text modalities; the additional track covered hour-long video understanding and introduced a novel video QA benchmark 1h-walk VQA. Overall, the tasks in the different tracks were: object tracking, point tracking, temporal action localisation, temporal sound localisation, multiple-choice video question-answering, grounded video question-answering, and hour-long video question-answering. We summarise in this report the challenge tasks and results, and introduce in detail the novel hour-long video QA benchmark 1h-walk VQA.
This paper proposes a concise, elegant, and robust pipeline to estimate smooth camera trajectories and obtain dense point clouds for casual videos in the wild. Traditional frameworks, such as ParticleSfM~\cite{zhao2022particlesfm}, address this problem by sequentially computing the optical flow between adjacent frames to obtain point trajectories. They then remove dynamic trajectories through motion segmentation and perform global bundle adjustment. However, the process of estimating optical flow between two adjacent frames and chaining the matches can introduce cumulative errors. Additionally, motion segmentation combined with single-view depth estimation often faces challenges related to scale ambiguity. To tackle these challenges, we propose a dynamic-aware tracking any point (DATAP) method that leverages consistent video depth and point tracking. Specifically, our DATAP addresses these issues by estimating dense point tracking across the video sequence and predicting the visibility and dynamics of each point. By incorporating the consistent video depth prior, the performance of motion segmentation is enhanced. With the integration of DATAP, it becomes possible to estimate and optimize all camera poses simultaneously by performing global bundle adjustments for point tracking classified as static and visible, rather than relying on incremental camera registration. Extensive experiments on dynamic sequences, e.g., Sintel and TUM RGBD dynamic sequences, and on the wild video, e.g., DAVIS, demonstrate that the proposed method achieves state-of-the-art performance in terms of camera pose estimation even in complex dynamic challenge scenes.
This paper presents an agile Unmanned Aerial Vehicle (UAV) landing control by considering the effect of ship's oscillations and moving, and also disturbance (i.e., crosswind) is considered. The presented control system can make the quadrotor UAV autonomously land whilst overcoming these adverse conditions, and the addition of a rudder beneath each propeller is designed to increase the yaw authority which is found to be lacking in heavy-lift quadrotor UAV. The PID flight control system is proposed based on reference-point tracking, allowing the UAV to follow any desired path in 3D space whilst simultaneously yawing to face any desired heading. Realistic saturation limits on actuator outputs to ensure the real-world performance of actuators. Disturbances include randomised gusting wind in 3 axes, and sensor noise on translation and rotation signals to represent noise from the GPS and accelerometer respectively. The results from the simulations demonstrate that the UAV is capable of landing on a ship which is moving with varying heading and oscillating vertically on ocean waves and has the ability to time its descent such that it meets the ship at the peak of a wave to minimise the relative velocity.
This paper introduces a method to enhance Interactive Imitation Learning (IIL) by extracting touch interaction points and tracking object movement from video demonstrations. The approach extends current IIL systems by providing robots with detailed knowledge of both where and how to interact with objects, particularly complex articulated ones like doors and drawers. By leveraging cutting-edge techniques such as 3D Gaussian Splatting and FoundationPose for tracking, this method allows robots to better understand and manipulate objects in dynamic environments. The research lays the foundation for more effective task learning and execution in autonomous robotic systems.
Recent advances in event-based vision suggest that these systems complement traditional cameras by providing continuous observation without frame rate limitations and a high dynamic range, making them well-suited for correspondence tasks such as optical flow and point tracking. However, there is still a lack of comprehensive benchmarks for correspondence tasks that include both event data and images. To address this gap, we propose BlinkVision, a large-scale and diverse benchmark with multiple modalities and dense correspondence annotations. BlinkVision offers several valuable features: 1) Rich modalities: It includes both event data and RGB images. 2) Extensive annotations: It provides dense per-pixel annotations covering optical flow, scene flow, and point tracking. 3) Large vocabulary: It contains 410 everyday categories, sharing common classes with popular 2D and 3D datasets like LVIS and ShapeNet. 4) Naturalistic: It delivers photorealistic data and covers various naturalistic factors, such as camera shake and deformation. BlinkVision enables extensive benchmarks on three types of correspondence tasks (optical flow, point tracking, and scene flow estimation) for both image-based and event-based methods, offering new observations, practices, and insights for future research. The benchmark website is https://www.blinkvision.net/.
Purpose: Tissue tracking is critical for downstream tasks in robot-assisted surgery. The Sparse Efficient Neural Depth and Deformation (SENDD) model has previously demonstrated accurate and real-time sparse point tracking, but struggled with occlusion handling. This work extends SENDD to enhance occlusion detection and tracking consistency while maintaining real-time performance. Methods: We use the Segment Anything Model2 (SAM2) to detect and mask occlusions by surgical tools, and we develop and integrate into SENDD an Adaptive Multi-Flow Sparse Tracker (A-MFST) with forward-backward consistency metrics, to enhance occlusion and uncertainty estimation. A-MFST is an unsupervised variant of the Multi-Flow Dense Tracker (MFT). Results: We evaluate our approach on the STIR dataset and demonstrate a significant improvement in tracking accuracy under occlusion, reducing average tracking errors by 12 percent in Mean Endpoint Error (MEE) and showing a 6 percent improvement in the averaged accuracy over thresholds of 4, 8, 16, 32, and 64 pixels. The incorporation of forward-backward consistency further improves the selection of optimal tracking paths, reducing drift and enhancing robustness. Notably, these improvements were achieved without compromising the model's real-time capabilities. Conclusions: Using A-MFST and SAM2, we enhance SENDD's ability to track tissue in real time under instrument and tissue occlusions.