This AI Clears Up Your Hazy Photos

dear fellow scholars this is two minute papers with károly FIFA here today we are going to talk about a paper that builds on a previous work by the name deep image priors dip in short this work was capable of performing JPEG compression artifact removal image in painting were in other words filling in parts of the image with data that makes sense super resolution and image denoising it was quite the package this new method is able to subdivide an image into a collection of layers which makes it capable of doing many seemingly unrelated tasks for instance one it can do image segmentation which typically means producing a mask that shows us the boundaries between the foreground and the background as an additional advantage it can also do this for videos as well too it can perform the hazing which can also be thought of as a deck and position tasks where the input is one image and the output is an image with haze and one with the objects hiding behind the haze if you spend the tiny bit of time looking at the window on a hazy day you will immediately see that this is immensely difficult mostly because of the fact that the amount of haze that we see is non-uniform along the landscape the AI has to detect and remove just the right amount of this haze and recover the original colors of the image and three it can also subdivide these crazy examples where two images are blended together in a moment I'll show you a better example with a complex texture where it is easier to see the utility of such a technique and for of course it can also perform image in painting which for instance can help us remove watermarks or other unwanted artifacts from our photos this case can also be thought of as an image layer plus the watermark layer and the algorithm is able to recover both of them as you see here on the right a tiny part of the content seems to bleed into the watermark layer but the results are still amazing it does this by using multiple of these dips deep image prior networks and goes by the name double-dip that one got me good when I first seen it you see here how it tries to reproduce this complex textured pattern as a sum of these two much simpler individual components the supplementary materials are available right in your browser and show you a ton of comparisons against other previous works here you see the results of these earlier works on image d hazing and see that indeed the new results are second to none and all this progress within only two years what a time to be alive if like me you'll have information theory who make sure to have a look at the paper and you'll be a happy person this episode has been supported by weights and biases provides tools to track your experiments in your deep learning projects it is like a shared logbook for your team and with this you can compare your own experiment results put them next to what your colleagues did and you can discuss your successes and failures much easier it takes less than five minutes to set up and is being used by open AI to yura research Stanford and Berkeley it was also used in this open AI project that you see here which we covered earlier in the series they reported that experiment tracking was crucial in this project and that this tool saved them quite a bit of time and money if only I had access to such a tool during our last research project where I had to compare the performance of neural networks for months and months well it turns out I will be able to get access to these tools because get this it's free and will always be free for academics and open source projects make sure to visit them through wendy be calm slash papers w AMD or just click the link in the video description and sign up for a free demo today our thanks to weights and biases for helping us make better videos for you thanks for watching and for your generous support and I'll see you next time