Related papers: DELTAv2: Accelerating Dense 3D Tracking

Multi-object tracking (MOT) is a vital component of intelligent video analytics applications such as surveillance and autonomous driving. The time and storage complexity required to execute deep learning models for visual object tracking…

A long-term visual object tracking performance evaluation methodology and a benchmark are proposed. Performance measures are designed by following a long-term tracking definition to maximize the analysis probing strength. The new measures…

In this paper, we propose a novel on-line visual tracking framework based on the Siamese matching network and meta-learner network, which run at real-time speeds. Conventional deep convolutional feature-based discriminative visual tracking…

We present a system for keyframe-based dense camera tracking and depth map estimation that is entirely learned. For tracking, we estimate small pose increments between the current camera image and a synthetic viewpoint. This significantly…

Multi-object tracking (MOT) at low frame rates can reduce computational, storage and power overhead to better meet the constraints of edge devices. Many existing MOT methods suffer from significant performance degradation in low-frame-rate…

Visual target tracking is one of the most sought-after yet challenging research topics in computer vision. Given the ill-posed nature of the problem and its popularity in a broad range of real-world scenarios, a number of large-scale…

In this thesis, we propose a pioneering work on sparse keypoints tracking across images using transformer networks. While deep learning-based keypoints matching have been widely investigated using graph neural networks - and more recently…

Tracking Any Point (TAP) has emerged as a fundamental tool for video understanding. Current approaches adapt Vision Foundation Models (VFMs) like DINOv2 via offline finetuning or test-time optimization. However, these VFMs rely on static…

Collecting high-quality data for training large-scale robotic models typically relies on real robot platforms, which is labor-intensive and costly, whether via teleoperation or scripted demonstrations. To scale data collection, many…

Online Multi-Object Tracking (MOT) from videos is a challenging computer vision task which has been extensively studied for decades. Most of the existing MOT algorithms are based on the Tracking-by-Detection (TBD) paradigm combined with…

Visual tracking is typically solved as a discriminative learning problem that usually requires high-quality samples for online model adaptation. It is a critical and challenging problem to evaluate the training samples collected from…

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…

In the recent literature, on the one hand, many 3D multi-object tracking (MOT) works have focused on tracking accuracy and neglected computation speed, commonly by designing rather complex cost functions and feature extractors. On the other…

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…

This paper presents DriveTrack, a new benchmark and data generation framework for long-range keypoint tracking in real-world videos. DriveTrack is motivated by the observation that the accuracy of state-of-the-art trackers depends strongly…

Annotating object ground truth in videos is vital for several downstream tasks in robot perception and machine learning, such as for evaluating the performance of an object tracker or training an image-based object detector. The accuracy of…

We present a pedestrian tracking algorithm, DensePeds, that tracks individuals in highly dense crowds (greater than 2 pedestrians per square meter). Our approach is designed for videos captured from front-facing or elevated cameras. We…

Object tracking is the cornerstone of many visual analytics systems. While considerable progress has been made in this area in recent years, robust, efficient, and accurate tracking in real-world video remains a challenge. In this paper, we…

3D face dense tracking aims to find dense inter-frame correspondences in a sequence of 3D face scans and constitutes a powerful tool for many face analysis tasks, e.g., 3D dynamic facial expression analysis. The majority of the existing…

Temporal consistency is critical in video prediction to ensure that outputs are coherent and free of artifacts. Traditional methods, such as temporal attention and 3D convolution, may struggle with significant object motion and may not…