Zobrazeno 1 - 10
of 1 095
pro vyhledávání: '"BROWN, Michael S."'
A popular method for enhancing images involves learning the style of a professional photo editor using pairs of training images comprised of the original input with the editor-enhanced version. When manipulating images, many editing tools offer a fea
Externí odkaz:
http://arxiv.org/abs/2407.09892
Autoexposure (AE) is a critical step applied by camera systems to ensure properly exposed images. While current AE algorithms are effective in well-lit environments with constant illumination, these algorithms still struggle in environments with brig
Externí odkaz:
http://arxiv.org/abs/2309.04542
3D lookup tables (3D LUTs) are a key component for image enhancement. Modern image signal processors (ISPs) have dedicated support for these as part of the camera rendering pipeline. Cameras typically provide multiple options for picture styles, wher
Externí odkaz:
http://arxiv.org/abs/2306.11920
Cameras and image-editing software often process images in the wide-gamut ProPhoto color space, encompassing 90% of all visible colors. However, when images are encoded for sharing, this color-rich representation is transformed and clipped to fit wit
Externí odkaz:
http://arxiv.org/abs/2304.11743
The assumption of a uniform light color distribution is no longer applicable in scenes that have multiple light colors. Most color constancy methods are designed to deal with a single light color, and thus are erroneous when applied to multiple light
Externí odkaz:
http://arxiv.org/abs/2211.08772
Autor:
Punnappurath, Abhijith, Abuolaim, Abdullah, Abdelhamed, Abdelrahman, Levinshtein, Alex, Brown, Michael S.
Many flagship smartphone cameras now use a dedicated neural image signal processor (ISP) to render noisy raw sensor images to the final processed output. Training nightmode ISP networks relies on large-scale datasets of image pairs with: (1) a noisy
Externí odkaz:
http://arxiv.org/abs/2206.02715
Most camera images are rendered and saved in the standard RGB (sRGB) format by the camera's hardware. Due to the in-camera photo-finishing routines, nonlinear sRGB images are undesirable for computer vision tasks that assume a direct relationship bet
Externí odkaz:
http://arxiv.org/abs/2206.01813
Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model (a.k.a., camera
Externí odkaz:
http://arxiv.org/abs/2206.01103
Noise modeling and reduction are fundamental tasks in low-level computer vision. They are particularly important for smartphone cameras relying on small sensors that exhibit visually noticeable noise. There has recently been renewed interest in using
Externí odkaz:
http://arxiv.org/abs/2206.00812
Portrait mode is widely available on smartphone cameras to provide an enhanced photographic experience. One of the primary effects applied to images captured in portrait mode is a synthetic shallow depth of field (DoF). The synthetic DoF (or bokeh ef
Externí odkaz:
http://arxiv.org/abs/2111.07837