31–40 of 179 posts
What camera are they shooting at 409,600 ISO at?
>Still images: ISO 100-102400 (expandable to ISO 50-409600),
[1]:https://www.sony.co.uk/electronics/interchangeable-lens-came...
It's surprising how little code [1] is needed to do this. On the other hand I feel this is quite dependent on the specific camera models and might not work on the RAW data downloaded from my phone. Happy to be corrected. [1] - https://github.com/cchen156/Learning-to-See-in-the-Dark/blob...
It's a huge amount of code, hidden behind the tensorflow import statements. It's common to credit GPUs for the rapid spread of deep learning, but good GPUs were available for quite a few years before deep learning really took off. As someone who wrote * a lot* of OpenCL code, including my own python wrappers, I'm fairly certain this code would be thousands of lines without a computation graph framework library. These…
“ The pretrained model probably not work for data from another camera sensor. We do not have support for other camera data. It also does not work for images after camera ISP, i.e., the JPG or PNG data.”
Would be cool to see how they come up with better models that would allow them to overcome the above limitations
I was just wondering a couple days ago why the image from my phone is so grainy, while my eyes+brain can see everything clear in the dark (it wasn't completely dark, of course). This seems to replicate the post-processing we do in our brain (which is also a giant neural network). I wonder if the process is similar?
That's not really a good analogy. You have a totally different sensor chemistry in your eyes, as well as different processing.
Earlier quoted context omitted.
It's a huge amount of code, hidden behind the tensorflow import statements. It's common to credit GPUs for the rapid spread of deep learning, but good GPUs were available for quite a few years before deep learning really took off. As someone who wrote * a lot* of OpenCL code, including my own python wrappers, I'm fairly certain this code would be thousands of lines without a computation graph framework library. These…
I don't know that I agree with this first statement, but even if I do, everything is abstracted by import statements even outside ML. You say this is a huge amount of code abstracted, but it wouldn't be difficult to reimplement this in numpy and pandas directly without using tensorflow at all. The code would expand a bit, and you'd have to deal directly with backprop and calculating derivatives but it wouldn't expand…
As a photographer, the comparison to "raw" results without color balance or noise removal seems somewhat deceptive. The effects visible in the video seem easy to quickly replicate with existing techniques, such as the "surface blur" filter that averages out pixel values in areas with similar color. This happens at the expense of detail in low-contrast areas, producing a plastic-like appearance of human skin and hair,…
Why is the "page suspended" ? http://cchen156.web.engr.illinois.edu/paper/18CVPR_SID.pdf
As a photographer, the comparison to "raw" results without color balance or noise removal seems somewhat deceptive. The effects visible in the video seem easy to quickly replicate with existing techniques, such as the "surface blur" filter that averages out pixel values in areas with similar color. This happens at the expense of detail in low-contrast areas, producing a plastic-like appearance of human skin and hair,…
Earlier quoted context omitted.
That's not really a good analogy. You have a totally different sensor chemistry in your eyes, as well as different processing.
And while brains are the original neural networks, they don't resemble what's going on with ML DNNs at all.