Related papers: Using Barriers to Reduce the Sensitivity to Edge M…

X-ray computed tomography is a powerful tool for volumetric imaging, where three-dimensional (3D) images are generated from a large number of individual X-ray projection images. Collecting the required number of low noise projection images…

In interactive object segmentation a user collaborates with a computer vision model to segment an object. Recent works employ convolutional neural networks for this task: Given an image and a set of corrections made by the user as input,…

Edges are the fundamental visual element for discovering tiny obstacles using a monocular camera. Nevertheless, tiny obstacles often have weak and inconsistent edge cues due to various properties such as small size and similar appearance to…

We present a refinement framework to boost the performance of pre-trained semi-supervised video object segmentation (VOS) models. Our work is based on scale inconsistency, which is motivated by the observation that existing VOS models…

Accurate height estimation from monocular aerial imagery presents a significant challenge due to its inherently ill-posed nature. This limitation is rooted in the absence of adequate geometric constraints available to the model when…

The problem of 3D object recognition is of immense practical importance, with the last decade witnessing a number of breakthroughs in the state of the art. Most of the previous work has focused on the matching of textured objects using…

The ultimate goal of many image-based modeling systems is to render photo-realistic novel views of a scene without visible artifacts. Existing evaluation metrics and benchmarks focus mainly on the geometric accuracy of the reconstructed…

This paper proposes a fast and online method for jointly performing 3D multi-object tracking and pose estimation using multiple monocular cameras. Our algorithm requires only 2D bounding box and pose detections, eliminating the need for…

Image prediction methods often struggle on tasks that require changing the positions of objects, such as video prediction, producing blurry images that average over the many positions that objects might occupy. In this paper, we propose a…

Specular reflections pose a significant challenge for object segmentation, as their sharp intensity transitions often mislead both conventional algorithms and deep learning based methods. However, as the specular reflection must lie on the…

Estimating the motion of the camera together with the 3D structure of the scene from a monocular vision system is a complex task that often relies on the so-called scene rigidity assumption. When observing a dynamic environment, this…

We propose a method to track the 6D pose of an object over time, while the object is under non-prehensile manipulation by a robot. At any given time during the manipulation of the object, we assume access to the robot joint controls and an…

The employment of convolutional neural networks has led to significant performance improvement on the task of object detection. However, when applying existing detectors to continuous frames in a video, we often encounter momentary…

Video object segmentation is a fundamental step in many advanced vision applications. Most existing algorithms are based on handcrafted features such as HOG, super-pixel segmentation or texture-based techniques, while recently deep features…

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…

Lidar point cloud distortion from moving object is an important problem in autonomous driving, and recently becomes even more demanding with the emerging of newer lidars, which feature back-and-forth scanning patterns. Accurately estimating…

Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video frames, enabling autonomous agents to reason about scene dynamics. However, existing state-of-the-art approaches are fully supervised and rely…

6D pose estimation of textureless objects is a valuable but challenging task for many robotic applications. In this work, we propose a framework to address this challenge using only RGB images acquired from multiple viewpoints. The core…

3D cameras have emerged as a critical source of information for applications in robotics and autonomous driving. These cameras provide robots with the ability to capture and utilize point clouds, enabling them to navigate their surroundings…

The current state-of-the-art in monocular 3D human pose estimation is heavily influenced by weakly supervised methods. These allow 2D labels to be used to learn effective 3D human pose recovery either directly from images or via 2D-to-3D…