Neighborhood operation - A neighborhood operation computes an output value at an image location using values from a surrounding set of input locations.
Neumann boundary condition - A Neumann boundary condition specifies the normal derivative of a function at the edge of a domain.
Neural radiance field - A neural radiance field, or NeRF, is a learned representation of a scene that predicts volume density and view-dependent color from spatial location and...
No-reference metric - A no-reference metric estimates image or video quality without requiring a matching pristine reference at evaluation time.
Noise reduction - Noise reduction is the process of reducing unwanted variation in a signal while trying to preserve useful information.
Non-blind deconvolution - Non-blind deconvolution estimates a sharp signal or image from a blurred observation when the blur model is supplied or treated as known.
Non-destructive editing - Non-destructive editing changes the appearance of an image while preserving the source data and keeping editing decisions revisable.
Non-linear editing - Non-linear editing is a video-editing method in which an editor can access and arrange recorded clips in any order on a timeline.
Non-local means (NLM) - Non-local means (NLM) is an image-denoising method that estimates a pixel from a weighted average of other pixels whose surrounding patches look similar.
Non-photorealistic rendering (NPR) - Non-photorealistic rendering (NPR) is the creation of images whose intended appearance differs from a realistic photograph.
Nonlinear filter - A nonlinear filter is a signal- or image-processing operation that does not obey the superposition property of a linear filter.
Normal distributions transform - The normal distributions transform, or NDT, represents local groups of spatial points with Gaussian distributions and can use that representation to align...
Normalized cross-correlation (NCC) - Normalized cross-correlation (NCC) measures the similarity of corresponding signal or image values after a normalization that reduces dependence on their...
Normalized cuts - Normalized cuts is a graph-partitioning approach that groups strongly connected items while penalizing connections broken between groups relative to each...
Nyquist sampling rate - The Nyquist sampling rate is twice the highest frequency present in a band-limited signal under the usual baseband sampling model.
Object co-segmentation - Object co-segmentation identifies and separates object regions that are shared across two or more images by analyzing the images together.
Object recognition - Object recognition is the process of identifying what an object is from visual information, such as an image or video.
Open set recognition - Open set recognition is a recognition setting in which a system must identify supported classes while allowing inputs from previously unseen classes to be...
Optical flow - Optical flow is the apparent movement of visual patterns across an image sequence, commonly represented by a two-dimensional vector at each estimated location.
Optimal transport - Optimal transport is a mathematical framework for finding the least costly way to redistribute one distribution of mass into another, according to a...
Oriented projective geometry - Oriented projective geometry is a form of projective geometry that retains a distinction between opposite homogeneous directions.
Orthographic projection - Orthographic projection maps three-dimensional points onto a plane along parallel lines perpendicular to that plane.
P-frame - A P-frame, or predictive frame, is a coded video picture that can use previously decoded reference pictures to predict image content.
Panorama - A panorama is an image showing an extended view of a scene, often created by combining overlapping photographs into one continuous composition.
Parallel projection - Parallel projection maps three-dimensional points onto a two-dimensional plane along parallel projection lines.
Path finding - Path finding is the process of finding a sequence of valid connections from a starting state to a destination.
Pattern grammar - A pattern grammar is a set of rules describing how simpler components can combine into structured patterns.
PDE / diffusion inpainting (Bertalmío) - PDE-based inpainting fills a selected missing or damaged image region using equations that propagate information from its surroundings.
Peak signal-to-noise ratio (PSNR) - Peak signal-to-noise ratio, or PSNR, is a logarithmic measure comparing the allowed peak signal range with the mean squared error between a test image and a...
Perception - distortion tradeoff - The perception - distortion tradeoff describes a tension in image reconstruction between matching an individual reference image according to a distortion...
Phase-based magnification - Phase-based magnification is a video-processing technique that makes small motions more visible by modifying temporal changes in the local phase of image...
Phase correlation - Phase correlation is a frequency-domain method for estimating the relative translation between two images.
Phase (Fourier) - Fourier phase describes the positional alignment of a sinusoidal component in a Fourier representation.
Photon counting noise - Photon counting noise is the random variation in the number of photons detected during a measurement interval.
Pink noise - Pink noise is a random signal whose power spectral density is approximately inversely proportional to frequency over a specified range.
Pixel connectivity - Pixel connectivity is the rule used to decide which neighboring pixels can belong to the same connected region.
Pixel-shift - Pixel-shift imaging combines multiple exposures captured with deliberate small shifts of the sensor or sampling position.
Planar (CHW) layout - Planar CHW layout represents an image with channel, height and width dimensions in that order.
Plenoptic function - The plenoptic function is a mathematical description of the light available along viewing directions from positions in space, across wavelength and time.
Point (range) operation - A point operation changes an image value using a mapping applied independently at each pixel location, without directly combining that pixel with...
Point sampling - Point sampling evaluates a signal at discrete positions or times to obtain sample values.
Point-set registration - Point-set registration estimates a transformation that aligns one collection of spatial points with another.
Point spread function - A point spread function, or PSF, describes how an imaging system represents an ideal point source.
Poisson equation - The Poisson equation is a partial differential equation that relates the Laplacian of an unknown function to a specified source term.
Poisson (gradient-domain) blending - Poisson blending is a gradient-domain image-editing method that reconstructs pixel values inside a selected region while matching chosen local differences...
Poisson noise - Poisson noise is random variation modeled using a Poisson distribution, commonly associated with counts of independently occurring events over a fixed...
Pooling - Pooling is an operation that summarizes a group of values into a smaller set of representative values.
Posterior - A posterior is a probability distribution updated using observed evidence within a specified model.