Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Wronski, Bartlomiej"'
Publikováno v:
Proceedings of the ACM on Computer Graphics and Interactive Techniques (2024), Volume 7, Issue 1, Article No:14, pp 1-20
2D texture maps and 3D voxel arrays are widely used to add rich detail to the surfaces and volumes of rendered scenes, and filtered texture lookups are integral to producing high-quality imagery. We show that applying the texture filter after evaluat
Externí odkaz:
http://arxiv.org/abs/2407.06107
Autor:
Vaidyanathan, Karthik, Salvi, Marco, Wronski, Bartlomiej, Akenine-Möller, Tomas, Ebelin, Pontus, Lefohn, Aaron
Publikováno v:
ACM Transactions on Graphics; Volume 42; Issue 4 (2023); Article No.: 88; pp 1-25
The continuous advancement of photorealism in rendering is accompanied by a growth in texture data and, consequently, increasing storage and memory demands. To address this issue, we propose a novel neural compression technique specifically designed
Externí odkaz:
http://arxiv.org/abs/2305.17105
2D texture maps and 3D voxel arrays are widely used to add rich detail to the surfaces and volumes of rendered scenes, and filtered texture lookups are integral to producing high-quality imagery. We show that filtering textures after evaluating light
Externí odkaz:
http://arxiv.org/abs/2305.05810
Autor:
Jiang, Yifan, Wronski, Bartlomiej, Mildenhall, Ben, Barron, Jonathan T., Wang, Zhangyang, Xue, Tianfan
Most image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to address this
Externí odkaz:
http://arxiv.org/abs/2201.00392
Autor:
Wronski, Bartlomiej
In the last decade Convolutional Neural Networks (CNNs) have defined the state of the art for many low level image processing and restoration tasks such as denoising, demosaicking, upscaling, or inpainting. However, on-device mobile photography is st
Externí odkaz:
http://arxiv.org/abs/2112.09318
We present a framework for interactive design of new image stylizations using a wide range of predefined filter blocks. Both novel and off-the-shelf image filtering and rendering techniques are extended and combined to allow the user to unleash their
Externí odkaz:
http://arxiv.org/abs/2002.10945
Autor:
Wronski, Bartlomiej, Garcia-Dorado, Ignacio, Ernst, Manfred, Kelly, Damien, Krainin, Michael, Liang, Chia-Kai, Levoy, Marc, Milanfar, Peyman
Compared to DSLR cameras, smartphone cameras have smaller sensors, which limits their spatial resolution; smaller apertures, which limits their light gathering ability; and smaller pixels, which reduces their signal-to noise ratio. The use of color f
Externí odkaz:
http://arxiv.org/abs/1905.03277
Publikováno v:
IET Computer Vision. 14:291-303
The authors present a framework for interactive design of new image stylisations using a wide range of predefined filter blocks. Both novel and off-the-shelf image filtering and rendering techniques are extended and combined to allow the user to unle
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6f1f75431fb76c2dea8fb900a52949c0
https://doi.org/10.1049/iet-cvi.2019.0787
https://doi.org/10.1049/iet-cvi.2019.0787
Autor:
Ignacio Garcia-Dorado, Manfred Ernst, Peyman Milanfar, Wronski Bartlomiej Maciej, Chia-Kai Liang, Marc Levoy, Michael Krainin, Damien Kelly
Compared to DSLR cameras, smartphone cameras have smaller sensors, which limits their spatial resolution; smaller apertures, which limits their light gathering ability; and smaller pixels, which reduces their signal-to noise ratio. The use of color f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24288fe51a5fe937a667bb9fedfdac25
http://arxiv.org/abs/1905.03277
http://arxiv.org/abs/1905.03277
Publikováno v:
IET Computer Vision (Wiley-Blackwell); Sep2020, Vol. 14 Issue 6, p291-303, 13p