Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Dillon Sharlet"'
Autor:
Andrew Adams, Dillon Sharlet
Publikováno v:
Proceedings of the ACM on Computer Graphics and Interactive Techniques. 5:1-8
Production imaging pipelines commonly operate using fixed-point arithmetic, and within these pipelines a core primitive is convolution by small filters - taking; convex combinations of fixed-point values in order to resample, interpolate, or denoise.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7da2afbf8b717e69425f6f48834509c2
https://doi.org/10.1145/3543869
https://doi.org/10.1145/3543869
Autor:
Yun-Ta Tsai, Tim Brooks, Yael Pritch, Nikhil Karnad, Dillon Sharlet, Orly Liba, Kiran Murthy, Marc Levoy, Ryan Geiss, Qiurui He, Tianfan Xue, Samuel W. Hasinoff, Jonathan T. Barron
Publikováno v:
ACM Transactions on Graphics. 38:1-16
Taking photographs in low light using a mobile phone is challenging and rarely produces pleasing results. Aside from the physical limits imposed by read noise and photon shot noise, these cameras are typically handheld, have small apertures and senso
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ef69e496b5fb9e18b84ff534d851ebc4
https://doi.org/10.1145/3355089.3356508
https://doi.org/10.1145/3355089.3356508
Autor:
Dillon Sharlet, Sylvain Paris, Jonathan Ragan-Kelley, Andrew Adams, Frédo Durand, Saman Amarasinghe, Connelly Barnes, Marc Levoy
Publikováno v:
Communications of the ACM. 61:106-115
Writing high-performance code on modern machines requires not just locally optimizing inner loops, but globally reorganizing computations to exploit parallelism and locality---doing things such as tiling and blocking whole pipelines to fit in cache.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e9be4b526f5bc629c07013e63899cf4
https://doi.org/10.1145/3150211
https://doi.org/10.1145/3150211
Publikováno v:
CVPR
Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to practical co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc93a937c9495780a4abd2d34ba1e7e6
https://doi.org/10.1109/cvpr.2019.01129
https://doi.org/10.1109/cvpr.2019.01129
Autor:
Jonathan T. Barron, Dillon Sharlet, Florian Kainz, Samuel W. Hasinoff, Andrew Adams, Ryan Geiss, Jiawen Chen, Marc Levoy
Publikováno v:
ACM Transactions on Graphics. 35:1-12
Cell phone cameras have small apertures, which limits the number of photons they can gather, leading to noisy images in low light. They also have small sensor pixels, which limits the number of electrons each pixel can store, leading to limited dynam
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2e021886b5546f435f348c8432b66378
https://doi.org/10.1145/2980179.2980254
https://doi.org/10.1145/2980179.2980254
Publikováno v:
ACM Transactions on Graphics. 35:1-11
The Halide image processing language has proven to be an effective system for authoring high-performance image processing code. Halide programmers need only provide a high-level strategy for mapping an image processing pipeline to a parallel machine
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::504b2805c8dc465b95a898bde9d5f094
https://doi.org/10.1145/2897824.2925952
https://doi.org/10.1145/2897824.2925952
Publikováno v:
CVPR
We present a technique for jointly denoising bursts of images taken from a handheld camera. In particular, we propose a convolutional neural network architecture for predicting spatially varying kernels that can both align and denoise frames, a synth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af2f4c4cde15d4d55c7d8d69d4b4698b
https://doi.org/10.1109/cvpr.2018.00265
https://doi.org/10.1109/cvpr.2018.00265
Publikováno v:
SIGGRAPH Courses
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e5f5c6d43ca411bb0133dc702c615546
https://doi.org/10.1145/2776880.2792710
https://doi.org/10.1145/2776880.2792710
Publikováno v:
ICRA
We present a novel realtime algorithm to compute the trajectory of each pedestrian in a crowded scene. Our formulation is based on an adaptive scheme that uses a combination of deterministic and probabilistic trackers to achieve high accuracy and eff
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::215c79c5b7922195811f7ad4bdaeacbf
https://doi.org/10.1109/icra.2014.6907095
https://doi.org/10.1109/icra.2014.6907095