Sort gallery by:
View:
Sony A7RII + Sony Zeiss 55mm f/1.8
EXIF: 55mm; 1/1600"; f/2.5; ISO100
gatto
Actitis hypoleucos
Actitis hypoleucos Sony A99Ii + Sony 300mm f/2.8 SSM II + TC 1,4x
EXIF: 420mm; 1/640"; f/8; ISO1000
actitis hypoleucos piro piro piccolo
Actitis hypoleucos
Actitis hypoleucos Sony A77II + Tamron 150-600mm f/5.6-6.3
EXIF: 600mm; 1/800"; f/8; ISO 800
actitis hypoleucos piro piro piccolo
Actitis hypoleucos
Actitis hypoleucos Sony A99II + Sony 300mm f/2.8 SSM II + TC 1,4x
EXIF: 420mm; 1/800"; f/9; ISO2000
actitis hypoleucos piro piro piccolo
Actitis hypoleucos
Actitis hypoleucos Piro piro piccolo
Sony A77II + Sony 300mm f/2.8 SSM II
EXIF: 300mm; 1/320"; f/5.6; ISO1250
actitis hypoleucos animali piro piro piccolo uccelli
Actitis hypoleucos
Actitis hypoleucos Sony A77II + Tamron 150-600 f/5-6.3x
EXIF: 600mm; 1/160"; f/8; ISO100
actitis hypoleucos piro piro piccolo
Aix galericulata
Aix galericulata Sony A77II + Sigma 10-20mm f/3.5
EXIF: 20mm; 1/50"; f/10; ISO400
aix galericulata anatra mandarina
Alcedo atthis
Alcedo atthis Sony A77II + Sigma 150-500
EXIF: 500mm; 1/100"; f/9.0; ISO800
alcedo atthis martin pescatore uccelli animali martin pescatore natura
Alcedo atthis (Martin pescatore)
Alcedo atthis (Martin pescatore) Sony A77II + Sony 300mm f/2.8 SSM II
EXIF: 300mm; 1/60"; f/5.6; ISO1250
alcedo atthis martin pescatore uccelli animali natura
Alghero by night
Alghero by night Sony A7RII + Zeiss Batis 25mm
WXIF: 25mm; 25"; f/8.0; ISO100
landscape paesaggio
Alguer
Alguer Sony A7RII + Zeiss Batis 25mm f/2
EXIF: 25mm; 1/640"; f/13; ISO100
city country
Angelo bianco (Ardea alba)
Angelo bianco (Ardea alba) Sony A77II + Tamron 150-600 f/5-6.3
EXIF: 560mm; 1/1600"; f/9.0; ISO400
airone bianco ardea alba

DPReview news

Articles: Digital Photography Review (dpreview.com)

All articles from Digital Photography Review
  • NVIDIA researchers can now turn 30fps video into 240fps slo-mo footage using AI

    NVIDIA researchers have developed a new method to extrapolate 240fps slow-motion video from 30fps content using artificial intelligence.

    Detailed in a paper submitted to the Cornell University Library, NVIDIA researchers trained the system by processing more than 11,000 videos through NVIDIA Tesla V100 GPUs and a cuDNN-accelerated PyTorch deep learning framework. This archive of videos, shot at 240fps, taught the system how to better predict the positioning differences in videos shot at only 30fps.

    This isn't the first time something like this has been done. A post-production plug-in called Twixtor has been doing this for almost a decade now. But it doesn't come anywhere close to NVIDIA's results in terms of quality and accuracy. Even in scenes where there is a great amount of detail, there appears to be minimal artifacts in the extrapolated frames.

    The researchers also note that while there are smartphones that can shoot 240fps video, it's not necessarily worth it to use all of that processing power and storage when something that will get you 99% of the way there is possible using a system such as theirs. 'While it is possible to take 240-frame-per-second videos with a cell phone, recording everything at high frame rates is impractical, as it requires large memories and is power-intensive for mobile devices,' the researchers wrote in the paper.

    The research and findings detailed in the paper will be presented at the annual Computer Vision and Pattern Recognition (CVPR) conference in Salt Lake City, Utah this week.

(C) 2017 Giuseppe Gessa