Related papers: AllTracker: Efficient Dense Point Tracking at High…
The last several years have seen significant progress in using depth cameras for tracking articulated objects such as human bodies, hands, and robotic manipulators. Most approaches focus on tracking skeletal parameters of a fixed shape…
We present a novel, realtime algorithm to compute the trajectory of each pedestrian in moderately dense crowd scenes. Our formulation is based on an adaptive particle filtering scheme that uses a multi-agent motion model based on…
Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and…
Event cameras, known for their high temporal resolution and ability to capture asynchronous changes, have gained significant attention for their potential in feature tracking, especially in challenging conditions. However, event cameras…
Video Panoptic Segmentation (VPS) aims to generate coherent panoptic segmentation and track the identities of all pixels across video frames. Existing methods predominantly utilize the trained instance embedding to keep the consistency of…
Six degree of freedom (6DoF) pose estimation for novel objects is a critical task in computer vision, yet it faces significant challenges in high-speed and low-light scenarios where standard RGB cameras suffer from motion blur. While event…
Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are suboptimal for dense…
The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching…
Our aim is to estimate the perspective-effected geometric distortion of a scene from a video feed. In contrast to all previous work we wish to achieve this using from low-level, spatio-temporally local motion features used in commercial…
Real-time tracking of small unmanned aerial vehicles (UAVs) on edge devices faces a fundamental resolution-speed conflict. Downsampling high-resolution imagery to standard detector input sizes causes small target features to collapse below…
Extending state-of-the-art object detectors from image to video is challenging. The accuracy of detection suffers from degenerated object appearances in videos, e.g., motion blur, video defocus, rare poses, etc. Existing work attempts to…
In operating rooms (OR), world-scale multi-view 3D tracking supports downstream applications such as surgeon behavior recognition, where physically meaningful quantities such as distances and motion statistics must be measured in meters.…
More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing…
We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images. DeepMatching relies on a hierarchical, multi-layer, correlational architecture designed for matching images and was inspired by…
In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection. Built upon the sparse query design in the PETR series, we systematically develop an object-centric temporal mechanism. The…
Interpreting motion captured in image sequences is crucial for a wide range of computer vision applications. Typical estimation approaches include optical flow (OF), which approximates the apparent motion instantaneously in a scene, and…
Accurate motion state estimation of Vulnerable Road Users (VRUs), is a critical requirement for autonomous vehicles that navigate in urban environments. Due to their computational efficiency, many traditional autonomy systems perform…
Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion. Despite its utility, the field of dense long-term tracking, especially over wide baselines, has not…
Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images. In this paper, we take…
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…