Live data from Hacker News

Bokehlicious Selfies

rahulrav.com

21–30 of 53 posts

Re: Bokehlicious Selfies

#21
if we're using deep learning anyways, might as well use a u-net (ie. pix2pix) to add the bokeh directly - this would require pair training data but would probably look a lot better visually.

Re: Bokehlicious Selfies

#22
I think I'm missing the part of my brain that lets me understand why bokeh selfies are even a thing. If you're going to remove your surroundings from the picture, why even bother taking a new picture?

Re: Bokehlicious Selfies

#23
post #9
post #4

This is really cool, but it isn't bokeh, it's just blur.

Yes. That is correct. Just wanted to see if the idea in my head actually worked. I was surprised by how decent it turned out especially given that I did not do anything “clever”.

One "clever" idea someone had was the use of the depth camera on the new iPhones to isolate the subject.

Rather than using a hardware solution, this is a good software solution that can be accomplished on more devices.

Re: Bokehlicious Selfies

#25
post #13

I just discovered that Zoom teleconferencing software has the ability to detect the background and replace it with an arbitrary video in real time. I have no idea how they do it, but it's as impressive as heck.

MS Teams can blur the background on video.

Re: Bokehlicious Selfies

#26
post #9
post #4

This is really cool, but it isn't bokeh, it's just blur.

Yes. That is correct. Just wanted to see if the idea in my head actually worked. I was surprised by how decent it turned out especially given that I did not do anything “clever”.

The image you used as an example already has some nice shallow depth of field from the beginning, which I think really helps make blend the effect in the end result. Did you try applying the effect to an actual selfie, which usually has more even focus?

Re: Bokehlicious Selfies

#27
post #13

I just discovered that Zoom teleconferencing software has the ability to detect the background and replace it with an arbitrary video in real time. I have no idea how they do it, but it's as impressive as heck.

Having just used it, it feels like a few factors: - a background scene is usually static. if a pixel matches its historical average (i e. not changing) then it's probably background. - if a pixel color matches its neighbors, it's probably the same as them. i noticed my black shirt tripped it up on occasion, but was all-or-nothing. - people are blobs, not diffuse, so try to segment large regions.

Yes, it did not work for me sitting with a laptop on a swing chair. It actually works better with clear static features in the background, but it seams to be a bit more (cnn?) because it seams to isolate paintings on the wall for me as well. Wish there was more open source easy to use camera stream manipulation. Skype also has background blurring.

Re: Bokehlicious Selfies

#28
post #13

I just discovered that Zoom teleconferencing software has the ability to detect the background and replace it with an arbitrary video in real time. I have no idea how they do it, but it's as impressive as heck.

It is a good early version of such a feature, but I've found it to fail fairly quickly in uneven light or with busy backgrounds. Still, it is a great feature, so I'm hopeful that they'll keep improving it and other services will match it.

Re: Bokehlicious Selfies

#29
post #13

I just discovered that Zoom teleconferencing software has the ability to detect the background and replace it with an arbitrary video in real time. I have no idea how they do it, but it's as impressive as heck.

MS Teams can blur the background on video.

Jitsi has this feature in beta too. It works pretty well, although it currently uses way too much CPU, and doesn't work quite as well as it does in MS Teams.
Post reply on HN