Depth of Field (abbreviated DOF in professional documentation) is the range of distance within a shot where objects appear acceptably sharp and in focus. A shallow depth of field means only a narrow slice of the frame is in focus while the rest falls into blur, whereas a deep depth of field keeps most or all of the image sharp from foreground to background.

Depth of field is controlled by three primary factors: aperture size, focal length, and distance to subject. A wider aperture produces shallower depth of field, longer focal lengths reduce depth of field, and closer focusing distances also decrease it. In professional cinematography and photography, depth of field is one of the most powerful compositional tools available, used to isolate subjects from distracting backgrounds, create visual separation between depth planes, and direct viewer attention with surgical precision. Shallow depth of field is associated with cinematic, high-production-value imagery, while deep depth of field is common in documentary, landscape, and architectural work where environmental context matters.

In AI image and video generation, depth of field can be specified through prompt language or reference images to control how much of the frame should be in focus. Models trained on photographic and cinematic content understand this concept well and can produce convincing depth-of-field effects, including realistic bokeh and gradual focus falloff that mimics optical characteristics of real camera lenses.