Texture synthesis - Texture synthesis creates new image content with the visual character of a texture, such as woven fabric, stone, or scattered leaves.
The Bitter Lesson - The Bitter Lesson is Richard Sutton's 2019 argument that broadly applicable methods able to use increasing computation, especially search and learning, have...
Tone curve - A tone curve is a mapping from input image values to output values, used to adjust brightness and contrast across different tonal ranges.
Tone mapping - Tone mapping transforms image brightness values to suit a display or output medium, especially when the captured or rendered scene has a wider dynamic range...
Train/validation/test split - A train/validation/test split divides a dataset into parts with different roles: training fits a model, validation guides development choices, and testing...
Transcript-based editing - Transcript-based editing is a way to edit recorded speech and its associated media by selecting and arranging words in a time-linked transcript.
Trifocal tensor - The trifocal tensor is a mathematical representation of the projective geometry connecting three camera views.
Tweedie's formula - Tweedie's formula relates a Bayesian estimate of an underlying signal to the probability distribution of its noisy observations.
Two-image operation - A two-image operation combines corresponding pixel values from two images to produce an output image.
Two-scale (base/detail) decomposition - A two-scale, or base/detail, decomposition separates an image into a base layer describing broader variation and a detail layer describing what remains.
Two-scale blending - Two-scale blending combines images by treating broad tonal variation and fine detail differently.
Two-scale style transfer - Two-scale style transfer changes a photograph's appearance by treating broad tonal structure and local detail separately, using a reference image to guide...
U-Net - U-Net is a convolutional neural-network architecture that combines an image encoder, an image decoder, and connections between corresponding resolution levels.
Unsharp mask - An unsharp mask is a sharpening operation that compares an image with a blurred version and adds a scaled copy of their difference back to the original.
V-cycle - A V-cycle is a multigrid procedure that moves from a fine representation of a problem down through coarser levels and then returns to the fine level with...
Vibrance - Vibrance is an image-editing control that adjusts color intensity selectively rather than applying one uniform saturation change everywhere.
Video content analysis - Video content analysis is the automated examination of video to extract information about what appears or happens over time.
Video imprint (computer vision) - A video imprint is a compact learned representation that aligns recurring visual features across video frames while retaining links back to where those...
Video magnification - Video magnification is the amplification of selected small changes over time in a video so that they become easier to see.
View morphing - View morphing is an image-based technique for creating transitions between views using projective geometry.
Viola - Jones object detection framework - The Viola - Jones object detection framework is a classical approach that combines efficiently computed rectangular image features, boosting-based feature...
Visibility mask - A visibility mask records which image locations provide visible, usable evidence for a particular view or synthesis step.
Visible differences predictor (VDP) - A visible differences predictor (VDP) is a perceptual image-comparison model that estimates whether people would notice differences between a reference...
Visual hull - A visual hull is a three-dimensional volume consistent with an object's silhouettes from a specified set of viewpoints.
Visual microphone - A visual microphone is a method that estimates sound from tiny sound-induced vibrations visible in video of an object.
Visual routine - A visual routine is a sequence of elementary visual operations used to determine a shape property or spatial relationship.
Visual temporal attention - Visual temporal attention is a mechanism that assigns different importance to visual information from different times in a sequence.
Visual tracking - Visual tracking is the estimation of an object's location or state across a sequence of images while maintaining correspondence with the same target over time.
Visual Turing Test - A Visual Turing Test is an evaluation approach that probes a computer vision system through questions about visual content.
Von Kries adaptation - Von Kries adaptation is a model of chromatic adaptation in which the three cone-response channels are adjusted by separate multiplicative gains.
Ward histogram-based tone mapping - Ward histogram-based tone mapping is a high-dynamic-range image reproduction approach that adjusts a luminance histogram to fit a display's range while...
Warp (image warping) - An image warp is a geometric transformation that changes where image content appears by mapping coordinates between a source image and a destination image.
Watershed segmentation - Watershed segmentation is an image-partitioning method that treats a numerical image as a landscape and separates the regions reached by competing floods.
Wavefront coding - Wavefront coding is a computational imaging approach that deliberately modifies an optical system's phase response and then digitally reconstructs the...
Weak learner - A weak learner is a learning algorithm that can produce a predictor with a modest advantage over a specified baseline under stated conditions.
Weiss intrinsic-image estimator - The Weiss intrinsic-image estimator is a method for separating a fixed reflectance image from changing illumination in an image sequence.
White-patch assumption - The white-patch assumption is a color-constancy assumption that strong image responses provide evidence of the scene illuminant because suitably reflective...
Wide-angle portrait correction - Wide-angle portrait correction is image processing that reduces unwanted shape stretching or skew in people photographed with a wide field of view.
Wiener filter - A Wiener filter is a filter designed to minimize expected squared estimation error within a specified class of linear filters, using statistical information...
Zippering - Zippering is an image artifact in which alternating light, dark or colored pixels create a tooth-like pattern along an edge.