Hybrid image

Last updated
A hybrid image (top) constructed from low-frequency components of a photograph of Marilyn Monroe (left inset) and high-frequency components of a photograph of Albert Einstein (right inset). Hybrid image decomposition.jpg
A hybrid image (top) constructed from low-frequency components of a photograph of Marilyn Monroe (left inset) and high-frequency components of a photograph of Albert Einstein (right inset).

A hybrid image is an image that is perceived in one of two different ways, depending on viewing distance, based on the way humans process visual input. A technique for creating hybrid images exhibiting this optical illusion was developed by Aude Oliva of MIT and Philippe G. Schyns of University of Glasgow, a method they originally proposed in 1994. Hybrid images combine the low spatial frequencies of one picture with the high spatial frequencies of another picture, producing an image with an interpretation that changes with viewing distance. [1]

Contents

Perhaps the most familiar example is one featuring Albert Einstein and Marilyn Monroe. Looking at the picture from a short distance, one can see a sharp image of Einstein, with only a hint of blurry distortion hinting at the presence of an overlaid image. Viewed from a distance in which the fine detail blurs, the unmistakable face of Monroe emerges. [2]

Related Research Articles

<span class="mw-page-title-main">Space</span> Framework of distances and directions

Space is a three-dimensional continuum containing positions and directions. In classical physics, physical space is often conceived in three linear dimensions. Modern physicists usually consider it, with time, to be part of a boundless four-dimensional continuum known as spacetime. The concept of space is considered to be of fundamental importance to an understanding of the physical universe. However, disagreement continues between philosophers over whether it is itself an entity, a relationship between entities, or part of a conceptual framework.

<span class="mw-page-title-main">Spacetime</span> Mathematical model combining space and time

In physics, spacetime, also called the space-time continuum, is a mathematical model that fuses the three dimensions of space and the one dimension of time into a single four-dimensional continuum. Spacetime diagrams are useful in visualizing and understanding relativistic effects, such as how different observers perceive where and when events occur.

Coherence expresses the potential for two waves to interfere. Two monochromatic beams from a single source always interfere. Wave sources are not strictly monochromatic: they may be partly coherent. Beams from different sources are mutually incoherent.

<span class="mw-page-title-main">Depth perception</span> Visual ability to perceive the world in 3D

Depth perception is the ability to perceive distance to objects in the world using the visual system and visual perception. It is a major factor in perceiving the world in three dimensions. Depth perception happens primarily due to stereopsis and accommodation of the eye.

<span class="mw-page-title-main">Autostereogram</span> Visual illusion of 3D scene achieved by unfocusing eyes when viewing specific 2D images

An autostereogram is a two-dimensional (2D) image that can create the optical illusion of a three-dimensional (3D) scene. Autostereograms use only one image to accomplish the effect while normal stereograms require two. The 3D scene in an autostereogram is often unrecognizable until it is viewed properly, unlike typical stereograms. Viewing any kind of stereogram properly may cause the viewer to experience vergence-accommodation conflict.

A grating is any regularly spaced collection of essentially identical, parallel, elongated elements. Gratings usually consist of a single set of elongated elements, but can consist of two sets, in which case the second set is usually perpendicular to the first. When the two sets are perpendicular, this is also known as a grid or a mesh.

<span class="mw-page-title-main">Einstein ring</span> Feature seen when light is gravitationally lensed by an object

An Einstein ring, also known as an Einstein–Chwolson ring or Chwolson ring, is created when light from a galaxy or star passes by a massive object en route to the Earth. Due to gravitational lensing, the light is diverted, making it seem to come from different places. If source, lens, and observer are all in perfect alignment (syzygy), the light appears as a ring.

<span class="mw-page-title-main">Philippe Halsman</span> American photographer

Philippe Halsman was an American portrait photographer. He was born in Riga in the part of the Russian Empire which later became Latvia, and died in New York City.

<span class="mw-page-title-main">Bohr–Einstein debates</span> Series of public disputes between physicists Niels Bohr and Albert Einstein

The Bohr–Einstein debates were a series of public disputes about quantum mechanics between Albert Einstein and Niels Bohr. Their debates are remembered because of their importance to the philosophy of science, insofar as the disagreements—and the outcome of Bohr's version of quantum mechanics becoming the prevalent view—form the root of the modern understanding of physics. Most of Bohr's version of the events held in the Solvay Conference in 1927 and other places was first written by Bohr decades later in an article titled, "Discussions with Einstein on Epistemological Problems in Atomic Physics". Based on the article, the philosophical issue of the debate was whether Bohr's Copenhagen interpretation of quantum mechanics, which centered on his belief of complementarity, was valid in explaining nature. Despite their differences of opinion and the succeeding discoveries that helped solidify quantum mechanics, Bohr and Einstein maintained a mutual admiration that was to last the rest of their lives.

Image resolution is the level of detail of an image. The term applies to digital images, film images, and other types of images. "Higher resolution" means more image detail. Image resolution can be measured in various ways. Resolution quantifies how close lines can be to each other and still be visibly resolved. Resolution units can be tied to physical sizes, to the overall size of a picture, or to angular subtense. Instead of single lines, line pairs are often used, composed of a dark line and an adjacent light line; for example, a resolution of 10 lines per millimeter means 5 dark lines alternating with 5 light lines, or 5 line pairs per millimeter. Photographic lens are most often quoted in line pairs per millimeter.

<span class="mw-page-title-main">Ambiguous image</span> Image that exploits graphical similarities between two or more distinct images

Ambiguous images or reversible figures are visual forms that create ambiguity by exploiting graphical similarities and other properties of visual system interpretation between two or more distinct image forms. These are famous for inducing the phenomenon of multistable perception. Multistable perception is the occurrence of an image being able to provide multiple, although stable, perceptions.

<span class="mw-page-title-main">Aerial perspective</span> Atmospheric effects on the appearance of a distant object

Aerial perspective, or atmospheric perspective, refers to the effect the atmosphere has on the appearance of an object as viewed from a distance. As the distance between an object and a viewer increases, the contrast between the object and its background decreases, and the contrast of any markings or details within the object also decreases. The colours of the object also become less saturated and shift toward the background colour, which is usually bluish, but may be some other colour under certain conditions.

<span class="mw-page-title-main">Gaussian blur</span> Type of image blur produced by a Gaussian function

In image processing, a Gaussian blur is the result of blurring an image by a Gaussian function.

<span class="mw-page-title-main">Optical transfer function</span> Function that specifies how different spatial frequencies are captured by an optical system

The optical transfer function (OTF) of an optical system such as a camera, microscope, human eye, or projector specifies how different spatial frequencies are captured or transmitted. It is used by optical engineers to describe how the optics project light from the object or scene onto a photographic film, detector array, retina, screen, or simply the next item in the optical transmission chain. A variant, the modulation transfer function (MTF), neglects phase effects, but is equivalent to the OTF in many situations.

<span class="mw-page-title-main">Contrast (vision)</span> Visible difference in brightness or color

Contrast is the difference in luminance or color that makes an object visible against a background of different luminance or color. The human visual system is more sensitive to contrast than to absolute luminance; thus, we can perceive the world similarly despite significant changes in illumination throughout the day or across different locations.

<span class="mw-page-title-main">Photographic mosaic</span> Mosaic composed of smaller photographs

A photographic mosaic or photomosaic is a picture that has been divided into tiled sections, usually equal sized, each of which is replaced with another photograph that matches the target photo. When viewed at low magnifications, the individual pixels appear as the primary image, while close examination reveals that the image is in fact made up of many hundreds or thousands of smaller images. Most of the time they are a computer-created type of montage.

<span class="mw-page-title-main">Optimum HDTV viewing distance</span> Television placement for immersive experience

Optimum HDTV viewing distance is the distance that provides the viewer with the optimum immersive visual HDTV experience.

<span class="mw-page-title-main">Strip photography</span> Type of photographic technique

Strip photography, or slit photography, is a photographic technique of capturing a two-dimensional image as a sequence of one-dimensional images over time, in contrast to a normal photo which is a single two-dimensional image at one point in time. A moving scene is recorded, over a period of time, using a camera that observes a narrow strip rather than the full field. If the subject is moving through this observed strip at constant speed, they will appear in the finished photo as a visible object. Stationary objects, like the background, will be the same the whole way across the photo and appear as stripes along the time axis; see examples on this page.

Aude Oliva is a French professor of computer vision, neuroscience, and human-computer interaction at the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL).

<i>Gold Marilyn Monroe</i> 1962 artwork by Andy Warhol

Gold Marilyn Monroe is a screenprint painting by Andy Warhol based on a photograph of the actress Marilyn Monroe's face centered on a large gold-painted canvas. Warhol used silkscreen ink on synthetic polymer paint on canvas. It was completed in 1962, the same year as Monroe's death. The image of Monroe is a direct copy of a close-up photograph, a publicity still from her 1953 film Niagara.

References

  1. Aude Oliva, Antonio Torralba and Philippe G. Schyns (2006). "Hybrid images" (PDF). ACM Transactions on Graphics . 25 (3): 527–532. doi:10.1145/1141911.1141919. Archived from the original (PDF) on 2007-03-15. Retrieved 2007-04-23.
  2. ""Marilyn-Einstein" and other examples". Archived from the original on 2008-02-20. Retrieved 2008-02-02.