Depth perception was a puzzle to scientists and philosophers for hundreds of years. They could not understand how we can see a three-dimensional world with only a two dimensional or flat, retina in each eye. Today it is realized that the ability to perceive depth is no more amazing than any other perceptual accomplishment. We are able to make use of information, or cues, in the sensory input to “generate” the three dimensional world that we see. Thus, Depth perception is the visual ability to perceive the world in three dimensions. Depth perception allows the beholder to accurately judge the distance to an object.

In depth perception, we perceive spatial relationships, especially distances between objects, in three dimensions. The 3D dimensional world projects onto the curved surface at the back of the eye. Though curved, the surface is two-dimensional. Since we do not have direct access to the third dimension of visual space, the visual system has to utilise various sources of information in the projection of the 3D world onto both eyes to recover depth, distance and the 3D shape of objects. Depth perception exposits a number of cues, these are Pictorial cues, Binocular cues and Dynamic cues. Pictorial cues can operate when only one eye is looking.

The retinal image of a static object undergoes significant changes during ego motion. Under most conditions, humans have the ability to perceive that object correctly as stationary, despite the retinal changes. The pictorial cues, which suggest a concave room, compete with the perception of the actual convex object. A good movie, painting, or photograph can create a convincing sense of depth where none exists. These cues supply much of the information present in real three-dimensional scenes (Haber, 1980). Pictorial depth cues, when combined, they can create a powerful illusion of depth.

We constantly use the pictorial cues to gauge depth and judge distances. A wide range of depth information can be directly extracted from a static monocular (& natural) image (Gibson 1979). In size as a pictorial cue, Objects that are placed further away from the horizon are seen as nearer. Larger objects are seen as closer, a retinal image of a small car is also interpreted as a distant car. Linear perspective – provides a strong cue to distance that can affect apparent size. Gibson pointed to the role of texture gradients as a cue to distance along surfaces.

In texture gradients, Changes in texture also contributes to depth perception. If you stand in the middle of a cobblestone street, the street will look coarse near your feet. However, its texture will get smaller and finer if you look into the distance. Another pictorial cue; highlights and shadows can provide information about an object's dimensions and depth. Because our visual system assumes the light comes from above, a totally different perception is obtained if the image is viewed upside down. Studies have shown that blur can act as a pictorial cue to depth perception.

But blurring a stimulus reduces its contrast, and contrast can act as a pictorial cue to depth perception. Interposition cues occur when there is overlapping of objects. The overlapped object is considered further away. Occlusion (blocking the sight) of objects by other objects is a clue, albeit a weak one, for judging relative distance. It only allows the beholder to create a "ranking" of nearness, but does not give any insight as to actual distances. In the absence of colour vision or binocular vision (as with one-eyed creatures) occlusion often serves as the method of last resort for providing rudimentary depth perception.

Binocular cues: Most of us, though, look out at the world with both eyes simultaneously, and we are thus able to add the binocular cues for depth perception to the monocular ones. By far the most important binocular cue depends upon the fact that the two eyes- retain-receive slightly different, or disparate, views of the world. Therefore, this cue is known as retinal disparity. Stereopsis is an important binocular cue to depth perception (Julesz 1971, and Marr & Poggio 1979). Stereopsis is the ability to distinguish the relative distance of objects with an apparent physical displacement between the objects.

Therefore, two objects stimulate disparate (non-corresponding) retinal points within Panum's fusional area. When one looks at a raised 3D square parts of the scene at the left edge of the square are visible by the left eye but not the right and the symmetrical relationship holds for the right side of the object. The object occludes the background in a different way for the two eyes and a binocular correspondence cannot be made yet this binocular occlusion cue can itself give rise to a depth percept (Shimojo and Nakayama 1990). Adaptable behaviour in visual world requires us to perceive movement accurately.

When our head move from side to side, objects at different distances move at a different relative velocity. Closer objects move "against" the direction of head movement and farther objects move "with" the direction of head movement. When you look out of the side window of a car or a train, you see close objects translating very fast (bushes) and distant objects passing very slow (mountains) or even being stationary (sun). This is the inverse relation between angular speed and distance, called motion parallax (Rogers & Graham 1982). Dynamic cue: 3-D structure is perceived from both actively generated and passively observed motion.

In passive viewing, motion must be computed simultaneously with structure. In active vision, on the other hand, extra-retinal information about motion is available, and in principle could be used to help compute structure. Random-dot techniques were used to examine the interactions between the depth cues of dynamic occlusion and motion parallax in the perception of three-dimensional (3-D) structures, in two different situations: (a) when an observer moved laterally with respect to a rigid 3-D structure, and (b) when surfaces at different distances moved with respect to a stationary observer.

In condition (a), the extent of accretion/deletion (dynamic occlusion) and the amount of relative motion (motion parallax) were both linked to the motion of the observer. When the two cues specified opposite, and therefore contradictory, depth orders, the perceived order in depth of the simulated surfaces was dependent on the magnitude of the depth separation. For small depth separations, motion parallax determined the perceived order, whereas for large separations it was determined by dynamic occlusion. In condition (b), the motion parallax cues for depth order were inherently ambiguous.

Conflicting depth and size information can lead to ambiguities. The size of the image of an object on the retina of the eye depends upon the distance of the object from the eye. An image of the same size can be produced on the retina by a nearby small object and larger object at some distance. People somehow automatically use information about distance and background to “correct” the size of the retinal image. The size constancy effect is sometimes believed to be the basis of the Ponzo illusion. There exist a lot of 3D technologies.

Most of them just only transfer 3D data into a 2D image. One of the technologies which could be truly called 3D is stereoscopic visualization. Only this stereoscopic 3D visualization shows all dimensions of the objects. Stereoscopy, stereoscopic imaging or 3-D (three-dimensional) imaging is a technique capable of recording three-dimensional visual information or creating the illusion of depth in an image. Presenting a slightly different image to each eye creates the illusion of depth in a photograph, movie, or other two-dimensional image.

There are passive, active, and auto stereoscopic monitor and anaglyph technology to exploit depth perception. Anaglyph images are produced using colour filters or computer image processing techniques to combine images from two slightly different viewpoints into a single image. Viewing anaglyphs through appropriately coloured glasses, results in each eye seeing a slightly different picture. For example, Spy Kids 3D was commercially successful in theatres using anaglyph paper glasses in 2003.