Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Miika Aittala"'
Publikováno v:
ACM Transactions on Graphics. 38:1-12
Denoising has proven to be useful to efficiently generate high-quality Monte Carlo renderings. Traditional pixel-based denoisers exploit summary statistics of a pixel's sample distributions, which discards much of the samples' information and limits
Publikováno v:
ACM Transactions on Graphics. 37:1-11
Gradient-based methods are becoming increasingly important for computer graphics, machine learning, and computer vision. The ability to compute gradients is crucial to optimization, inverse problems, and deep learning. In rendering, the gradient is r
Publikováno v:
Computer Graphics Forum
Computer Graphics Forum, 2021, 40 (4), ⟨10.1111/cgf.14342⟩
Computer Graphics Forum, Wiley, 2021, 40 (4)
Computer Graphics Forum, 2021, 40 (4), ⟨10.1111/cgf.14342⟩
Computer Graphics Forum, Wiley, 2021, 40 (4)
International audience; Image-Based Rendering allows users to easily capture a scene using a single camera and then navigate freely with realistic results. However, the resulting renderings are completely static, and dynamic effects – such as fire,
Publikováno v:
arXiv
ICCV
ICCV
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse problems involvi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b43b1e6b5287a5e01face690292f4ad0
http://arxiv.org/abs/1910.08131
http://arxiv.org/abs/1910.08131
Publikováno v:
Computer Graphics Forum
Computer Graphics Forum, 2019, 38, ⟨10.1111/cgf.13765⟩
arXiv
Computer Graphics Forum, Wiley, 2019, 38, ⟨10.1111/cgf.13765⟩
Computer Graphics Forum, 2019, 38, ⟨10.1111/cgf.13765⟩
arXiv
Computer Graphics Forum, Wiley, 2019, 38, ⟨10.1111/cgf.13765⟩
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by traditional optimiz
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e3bff1a47a20d2e54d2cdb9dc1ba7d2
https://hal.science/hal-02164993v2/document
https://hal.science/hal-02164993v2/document
Publikováno v:
CVPR
The style-based GAN architecture (StyleGAN) yields state-of-the-art results in data-driven unconditional generative image modeling. We expose and analyze several of its characteristic artifacts, and propose changes in both model architecture and trai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::409e87cc1c06b00b60341d7531b086a2
Publikováno v:
ACM Transactions on Graphics. 35(4):1-13
We extend parametric texture synthesis to capture rich, spatially varying parametric reflectance models from a single image. Our input is a single head-lit flash image of a mostly flat, mostly stationary (textured) surface, and the output is a tile o
Autor:
Frédo Durand, Miika Aittala
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012366
ECCV (8)
ECCV (8)
We propose a neural approach for fusing an arbitrary-length burst of photographs suffering from severe camera shake and noise into a sharp and noise-free image. Our novel convolutional architecture has a simultaneous view of all frames in the burst,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2e8b38e4e67655058405e5de270bf7db
https://doi.org/10.1007/978-3-030-01237-3_45
https://doi.org/10.1007/978-3-030-01237-3_45
Publikováno v:
ACM Transactions on Graphics
ACM Transactions on Graphics, Association for Computing Machinery, In press, 37, pp.128-143. ⟨10.1145/3197517.3201378⟩
arXiv
ACM Transactions on Graphics, In press, 37, pp.128-143. ⟨10.1145/3197517.3201378⟩
ACM Transactions on Graphics, Association for Computing Machinery, In press, 37, pp.128-143. ⟨10.1145/3197517.3201378⟩
arXiv
ACM Transactions on Graphics, In press, 37, pp.128-143. ⟨10.1145/3197517.3201378⟩
Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures. Yet, recovering spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a single image base
Publikováno v:
ACM Transactions on Graphics. 34:1-13
Material appearance acquisition usually makes a trade-off between acquisition effort and richness of reflectance representation. In this paper, we instead aim for both a light-weight acquisition procedure and a rich reflectance representation simulta