Related papers: 3D Trajectory Reconstruction of Dynamic Objects Us…
Tracking and reconstructing 3D objects from cluttered scenes are the key components for computer vision, robotics and autonomous driving systems. While recent progress in implicit function has shown encouraging results on high-quality 3D…
Reconstructing the underlying 3D surface of an object from a single image is a challenging problem that has received extensive attention from the computer vision community. Many learning-based approaches tackle this problem by learning a 3D…
Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging and benefits from…
Many man-made objects are characterised by a shape that is symmetric along one or more planar directions. Estimating the location and orientation of such symmetry planes can aid many tasks such as estimating the overall orientation of an…
Partial-view 3D recognition -- reconstructing 3D geometry and identifying object instances from a few sparse RGB images -- is an exceptionally challenging yet practically essential task, particularly in cluttered, occluded real-world…
We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i.e., unexposed, geometries of a target 3D object. Unlike other works…
A natural approach to generative modeling of videos is to represent them as a composition of moving objects. Recent works model a set of 2D sprites over a slowly-varying background, but without considering the underlying 3D scene that gives…
Semantic aware reconstruction is more advantageous than geometric-only reconstruction for future robotic and AR/VR applications because it represents not only where things are, but also what things are. Object-centric mapping is a task to…
Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation. Although recent methods achieve high-fidelity reconstructions, they either rely on costly human annotations for object…
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…
Object tracking is a key challenge of computer vision with various applications that all require different architectures. Most tracking systems have limitations such as constraining all movement to a 2D plane and they often track only one…
A first-principle single-object model is proposed for pedestrian tracking. It is assumed that the extent of the moving object can be described via known statistics in 3D, such as pedestrian height. The proposed model thus need not constrain…
AR/VR applications and robots need to know when the scene has changed. An example is when objects are moved, added, or removed from the scene. We propose a 3D object discovery method that is based only on scene changes. Our method does not…
Moving objects are frequently seen in daily life and usually appear blurred in images due to their motion. While general object retrieval is a widely explored area in computer vision, it primarily focuses on sharp and static objects, and…
Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first…
Many applications such as autonomous navigation, urban planning and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper we propose to automatically detect and compute the…
Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes…
Numerous methods for human activity recognition have been proposed in the past two decades. Many of these methods are based on sparse representation, which describes the whole video content by a set of local features. Trajectories, being…
Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, this paper proposes a…
Standard RGB-D trackers treat the target as an inherently 2D structure, which makes modelling appearance changes related even to simple out-of-plane rotation highly challenging. We address this limitation by proposing a novel long-term…