Computational photography refers to digital image capture and processing techniques that use digital computation instead of optical processes. Computational photography can improve the capabilities of a camera, or introduce features that were not possible at all with film based photography, or reduce the cost or size of camera elements. Examples of computational photography include in-camera computation of digital panoramas, high-dynamic-range images, and light field cameras. Light field cameras use novel optical elements to capture three dimensional scene information which can then be used to produce 3D images, enhanced depth-of-field, and selective de-focusing (or "post focus"). Enhanced depth-of-field reduces the need for mechanical focusing systems. All of these features use computational imaging techniques.
The definition of computational photography has evolved to cover a number of
subject areas in computer graphics, computer vision, and applied
optics. These areas are given below, organized according to a taxonomy
proposed by Shree K. Nayar. Within each area is a list of techniques, and for
each technique one or two representative papers or books are cited.
Deliberately omitted from the
taxonomy are (see also )
techniques applied to traditionally captured
images in order to produce better images. Examples of such techniques are
dynamic range compression (i.e. tone mapping),
color management, image completion (a.k.a. inpainting or hole filling),
digital watermarking, and artistic image effects.
Also omitted are techniques that produce range data,
volume data, 3D models, 4D light fields,
4D, 6D, or 8D BRDFs, or other high-dimensional image-based representations. Epsilon photography is a sub-field of computational photography.
Photos taken using computational photography can allow amateurs to produce photographs rivalling the quality of professional photographers, but currently (2019) do not outperform the use of professional-level equipment.
This is controlling photographic illumination in a structured fashion, then processing the captured images,
to create new images.
Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.
Visual computing and machine learning are characterized by their reliance on numerical algorithms to process large amounts of information such as images, shapes, and 3D volumes. This course will famil
The students will gain the theoretical knowledge in computational photography, which allows recording and processing a richer visual experience than traditional digital imaging. They will also execute
This summer school is an hands-on introduction on the fundamentals of image analysis for scientists. A series of lectures provide students with the key concepts in the field, and are followed by pract
L'imagerie à grande gamme dynamique (ou imagerie large-gamme) (high-dynamic-range imaging ou HDRI) regroupe un ensemble de techniques numériques permettant de présenter une image fixe ou animée d'une scène qui présente, dans ses diverses parties, des niveaux très différents de luminosité. Une se constitue à partir de pixels auxquels est associé un triplet de valeurs qui en indique la luminosité et la couleur. Le rendu à grande dynamique concerne des fichiers d'origine où les pixels ont plus de valeurs possibles que les écrans ou imprimantes du rendu.
La vision par ordinateur est un domaine scientifique et une branche de l’intelligence artificielle qui traite de la façon dont les ordinateurs peuvent acquérir une compréhension de haut niveau à partir d's ou de vidéos numériques. Du point de vue de l'ingénierie, il cherche à comprendre et à automatiser les tâches que le système visuel humain peut effectuer. Les tâches de vision par ordinateur comprennent des procédés pour acquérir, traiter, et « comprendre » des images numériques, et extraire des données afin de produire des informations numériques ou symboliques, par ex.
Explore les concepts de vision stéréoscopique tels que les occlusions, l'impact de la taille de la fenêtre, la stéréo multivue, la reconstruction dynamique de la forme et la segmentation basée sur des graphiques.
We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cas ...
IEEE COMPUTER SOC2022
, , ,
Megapixel single-photon avalanche diode (SPAD) arrays have been developed recently, opening up the possibility of deploying SPADs as general-purpose passive cameras for photography and computer vision. However, most previous work on SPADs has been limited ...
Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection. However, existing CNN based pulmonary nodule detection methods lack the ability to capture long-range dependencies, which is vita ...