相关论文: DATAP-SfM: Dynamic-Aware Tracking Any Point for Ro…

Point cloud maps generated via LiDAR sensors using extensive remotely sensed data are commonly used by autonomous vehicles and robots for localization and navigation. However, dynamic objects contained in point cloud maps not only downgrade…

Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ…

We introduce TAPIP3D, a novel approach for long-term 3D point tracking in monocular RGB and RGB-D videos. TAPIP3D represents videos as camera-stabilized spatio-temporal feature clouds, leveraging depth and camera motion information to lift…

With the advance of fluorescence imaging technologies, recently cell biologists are able to record the movement of protein vesicles within a living cell. Automatic tracking of the movements of these vesicles become key for qualitative…

The goal of this paper is to discover, segment, and track independently moving objects in complex visual scenes. Previous approaches have explored the use of optical flow for motion segmentation, leading to imperfect predictions due to…

Tracking dense 3D motion from monocular videos remains challenging, particularly when aiming for pixel-level precision over long sequences. We introduce DELTA, a novel method that efficiently tracks every pixel in 3D space, enabling…

Simultaneous Localization and Mapping (SLAM) is considered an ever-evolving problem due to its usage in many applications. Evaluation of SLAM is done typically using publicly available datasets which are increasing in number and the level…

Video privacy leakage is becoming an increasingly severe public problem, especially in cloud-based video surveillance systems. It leads to the new need for secure cloud-based video applications, where the video is encrypted for privacy…

This paper addresses the problem of multi-object tracking in Unmanned Aerial Vehicle (UAV) footage. It plays a critical role in various UAV applications, including traffic monitoring systems and real-time suspect tracking by the police.…

Recent geometric methods need reliable estimates of 3D motion parameters to procure accurate dense depth map of a complex dynamic scene from monocular images \cite{kumar2017monocular, ranftl2016dense}. Generally, to estimate…

Multi-object tracking (MOT) in computer vision remains a significant challenge, requiring precise localization and continuous tracking of multiple objects in video sequences. The emergence of data sets that emphasize robust…

We present an algorithm (SOFAS) to estimate the optical flow of events generated by a dynamic vision sensor (DVS). Where traditional cameras produce frames at a fixed rate, DVSs produce asynchronous events in response to intensity changes…

As an important pillar of underwater intelligence, Marine Animal Segmentation (MAS) involves segmenting animals within marine environments. Previous methods don't excel in extracting long-range contextual features and overlook the…

Humans excel at constructing panoramic mental models of their surroundings, maintaining object permanence and inferring scene structure beyond visible regions. In contrast, current artificial vision systems struggle with persistent,…

Multi-frame methods improve monocular depth estimation over single-frame approaches by aggregating spatial-temporal information via feature matching. However, the spatial-temporal feature leads to accuracy degradation in dynamic scenes. To…

Autonomous motion capture (mocap) systems for outdoor scenarios involving flying or mobile cameras rely on i) a robotic front-end to track and follow a human subject in real-time while he/she performs physical activities, and ii) an…

We propose Track and Caption Any Motion (TCAM), a motion-centric framework for automatic video understanding that discovers and describes motion patterns without user queries. Understanding videos in challenging conditions like occlusion,…

Point tracking aims to follow visual points through complex motion, occlusion, and viewpoint changes, and has advanced rapidly with modern foundation models. Yet progress toward general point tracking remains constrained by limited…

Current methods for dense 3D point tracking in dynamic scenes typically rely on pairwise processing, require known camera poses, or assume temporal ordering of input frames, thereby constraining their flexibility and applicability.…

Accurately and efficiently modeling dynamic scenes and motions is considered so challenging a task due to temporal dynamics and motion complexity. To address these challenges, we propose DynMF, a compact and efficient representation that…