Self-supervised learningSelf-supervised learning (SSL) is a paradigm in machine learning for processing data of lower quality, rather than improving ultimate outcomes. Self-supervised learning more closely imitates the way humans learn to classify objects. The typical SSL method is based on an artificial neural network or other model such as a decision list. The model learns in two steps. First, the task is solved based on an auxiliary or pretext classification task using pseudo-labels which help to initialize the model parameters.
ImageAn image is a visual representation of something. An image can be a two-dimensional (2D) representation, such as a drawing, painting, or photograph, or a three-dimensional (3D) object, such as a carving or sculpture. An image may be displayed through other media, including projection on a surface, activation of electronic signals, or digital displays. Two-dimensional images can be still or animated. Still images can usually be reproduced through mechanical means, such as photography, printmaking or photocopying.
Binocular disparityBinocular disparity refers to the difference in image location of an object seen by the left and right eyes, resulting from the eyes’ horizontal separation (parallax). The brain uses binocular disparity to extract depth information from the two-dimensional s in stereopsis. In computer vision, binocular disparity refers to the difference in coordinates of similar features within two stereo images. A similar disparity can be used in rangefinding by a coincidence rangefinder to determine distance and/or altitude to a target.
Camera obscuraA camera obscura (; ) is a darkened room with a small hole or lens at one side through which an is projected onto a wall or table opposite the hole. Camera obscura can also refer to analogous constructions such as a box or tent in which an exterior image is projected inside. Camera obscuras with a lens in the opening have been used since the second half of the 16th century and became popular as aids for drawing and painting.
Astigmatism (optical systems)An optical system with astigmatism is one where rays that propagate in two perpendicular planes have different foci. If an optical system with astigmatism is used to form an image of a cross, the vertical and horizontal lines will be in sharp focus at two different distances. The term comes from the Greek α- (a-) meaning "without" and στίγμα (stigma), "a mark, spot, puncture". There are two distinct forms of astigmatism. The first is a third-order aberration, which occurs for objects (or parts of objects) away from the optical axis.
Circle of confusionIn optics, a circle of confusion (CoC) is an optical spot caused by a cone of light rays from a lens not coming to a perfect focus when imaging a point source. It is also known as disk of confusion, circle of indistinctness, blur circle, or blur spot. In photography, the circle of confusion is used to determine the depth of field, the part of an image that is acceptably sharp. A standard value of CoC is often associated with each image format, but the most appropriate value depends on visual acuity, viewing conditions, and the amount of enlargement.
Schmidt cameraA Schmidt camera, also referred to as the Schmidt telescope, is a catadioptric astrophotographic telescope designed to provide wide fields of view with limited aberrations. The design was invented by Bernhard Schmidt in 1930. Some notable examples are the Samuel Oschin telescope (formerly Palomar Schmidt), the UK Schmidt Telescope and the ESO Schmidt; these provided the major source of all-sky photographic imaging from 1950 until 2000, when electronic detectors took over. A recent example is the Kepler space telescope exoplanet finder.
Vergence-accommodation conflictVergence-accommodation conflict (VAC), also known as accommodation-vergence conflict, is a visual phenomenon that occurs when the brain receives mismatching cues between vergence and accommodation of the eye. This commonly occurs in virtual reality devices, augmented reality devices, 3D movies, and other types of stereoscopic displays and autostereoscopic displays. The effect can be unpleasant and cause eye strain. Two main ocular responses can be distinguished - vergence of eyes and accommodation.
AcutanceIn photography, acutance describes a subjective perception of sharpness that is related to the edge contrast of an . Acutance is related to the amplitude of the derivative of brightness with respect to space. Due to the nature of the human visual system, an image with higher acutance appears sharper even though an increase in acutance does not increase real . Historically, acutance was enhanced chemically during development of a negative (high acutance developers), or by optical means in printing (unsharp masking).
