Related papers: Linton Stereo Illusion
Most existing algorithms for depth estimation from single monocular images need large quantities of metric groundtruth depths for supervised learning. We show that relative depth can be an informative cue for metric depth estimation and can…
Computationally efficient moving object detection and depth estimation from a stereo camera is an extremely useful tool for many computer vision applications, including robotics and autonomous driving. In this paper we show how moving…
To humans, a robin seems more like a bird than a bird seems like a robin, but does this asymmetry also hold for machine vision? Humans and modern vision models can match each other in accuracy while making systematically different kinds of…
Visualizing very large matrices involves many formidable problems. Various popular solutions to these problems involve sampling, clustering, projection, or feature selection to reduce the size and complexity of the original task. An…
This paper introduces depth estimation from water drops. The key idea is that a single water drop adhered to window glass is totally transparent and convex, and thus optically acts like a fisheye lens. If we have more than one water drop in…
We present a method for 3D reconstruction only using calibrated multi-view surface azimuth maps. Our method, multi-view azimuth stereo, is effective for textureless or specular surfaces, which are difficult for conventional multi-view…
Nighttime stereo depth estimation is still challenging, as assumptions associated with daytime lighting conditions do not hold any longer. Nighttime is not only about low-light and dense noise, but also about glow/glare, flares, non-uniform…
Under very general assumptions of metric theory of spacetime, photons traveling along null geodesics and photon number conservation, two observable concepts of cosmic distance, i.e. the angular diameter and the luminosity distances are…
This paper proposes an original problem of \emph{stereo computation from a single mixture image}-- a challenging problem that had not been researched before. The goal is to separate (\ie, unmix) a single mixture image into two constitute…
We propose a new way to hide the fifth dimension, and to modify gravity in the far infra-red. A gravitating tensional membrane in five dimensions folds the transverse space into a truncated cone, stoppered by the membrane. For near-critical…
Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging. In this paper, we propose Stereo Mixture Density Networks…
Learning depth and optical flow via deep neural networks by watching videos has made significant progress recently. In this paper, we jointly solve the two tasks by exploiting the underlying geometric rules within stereo videos.…
This study derives analytical expressions for the depth and range error of fisheye stereo vision systems as a function of object distance, specifically accounting for accuracy at large angles.
A neutron optical transport system is proposed which comprises nested short elliptical mirrors located halfway between two common focal points M and M'. It images cold neutrons from a diverging beam or a source with finite size at M by…
Stereo images have been captured primarily for 3D reconstruction in the past. However, the depth information acquired from stereo can also be used along with saliency to highlight certain objects in a scene. This approach can be used to…
A human creates an image basing on the information delivered by photons that arrived at his retina simultaneously. Due to finite and constant velocity of light these photons left the moving body at different times, since not all points of…
Traditional stereo algorithms have focused their efforts on reconstruction quality and have largely avoided prioritizing for run time performance. Robots, on the other hand, require quick maneuverability and effective computation to observe…
The Erd\H{o}s distinct distance problem is a ubiquitous problem in discrete geometry. Somewhat less well known is Erd\H{o}s' distinct angle problem, the problem of finding the minimum number of distinct angles between $n$ non-collinear…
This paper studies the properties of a new lower bound for the natural pseudo-distance. The natural pseudo-distance is a dissimilarity measure between shapes, where a shape is viewed as a topological space endowed with a real-valued…
Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…