Related papers: Visual appearance of wireframe objects in special …
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…
In this paper we propose to represent a scene as an abstraction of 'things'. We start from 'things' as generated by modern object proposals, and we investigate their immediately observable properties: position, size, aspect ratio and color,…
Deformable objects present a formidable challenge for robotic manipulation due to the lack of canonical low-dimensional representations and the difficulty of capturing, predicting, and controlling such objects. We construct compact…
We present a simple thought experiment in which a beam of light of a finite length (a light-pulse) enters a detection device that consists of a wave detector and a light bulb. We examine the experiment from the reference frame where the…
A robot that can operate in novel and unstructured environments must be capable of recognizing new, previously unseen, objects. In this work, a visual cue is used to specify a novel object of interest which must be localized in new…
We propose a method for annotating the location of objects in ImageNet. Traditionally, this is cast as an image window classification problem, where each window is considered independently and scored based on its appearance alone. Instead,…
Most of computer vision focuses on what is in an image. We propose to train a standalone object-centric context representation to perform the opposite task: seeing what is not there. Given an image, our context model can predict where…
Reconstruction of indoor surfaces with limited texture information or with repeated textures, a situation common in walls and ceilings, may be difficult with a monocular Structure from Motion system. We propose a Semantic Room Wireframe…
This paper addresses the problem of tracking moving objects of variable appearance in challenging scenes rich with features and texture. Reliable tracking is of pivotal importance in surveillance applications. It is made particularly…
Scattering can rapidly degrade our ability to form an optical image, to the point where only speckle-like patterns can be measured. Truly non-invasive imaging through a strongly scattering obstacle is difficult, and usually reliant on a…
Limited by the performance factor, it is arduous to recognize target object and locate it in Augmented Reality (AR) scenes on low-end mobile devices, especially which using monocular cameras. In this paper, we proposed an algorithm which…
Intuitively, the appearance of true object boundaries varies from image to image. Hence the usual monolithic approach of training a single boundary predictor and applying it to all images regardless of their content is bound to be…
Computer vision tasks typically involve describing what is present in an image (e.g. classification, detection, segmentation, and captioning). We study a visual common sense task that requires understanding what is not present.…
We propose novel motion representations for animating articulated objects consisting of distinct parts. In a completely unsupervised manner, our method identifies object parts, tracks them in a driving video, and infers their motions by…
An observer at rest in a uniformly accelerated reference frame experiences a parallel gravitational field, where the rays of light are formed as circular arcs instead of being straight lines. We deduce how a sphere at rest in the Rindler…
The theoretical framework of electromagnetism played a foundational role in Einstein's development of special relativity. To support conceptual understanding, we present a fully special relativistic computer simulation that visualizes…
The challenge of graphically rendering high frame-rate videos on low compute devices can be addressed through periodic prediction of future frames to enhance the user experience in virtual reality applications. This is studied through the…
We study the problem of unsupervised physical object discovery. While existing frameworks aim to decompose scenes into 2D segments based off each object's appearance, we explore how physics, especially object interactions, facilitates…
Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials and estimating their physical properties based purely on…
Deep learning is ubiquitous, but its lack of transparency limits its impact on several potential application areas. We demonstrate a virtual reality tool for automating the process of assigning data inputs to different categories. A dataset…