Depth-aware light injection in TypeGPU
@reczko_konrad7.6K followers
10,120,189 views
50 Comments
Comments from the original post on X (Twitter)

@reczko_konrad
Here are some fun intermediate textures, the depth and constructed normals
2,448 likes

@nandogarza
Really nice. But you shouldn't cast a shadow when the light source is between you and the wall
544 likes

@reczko_konrad
True, but it looks cool :D Doubles as fake godrays
687 likes

@marc_krenn
dope! what depth model are you using?
150 likes

@reczko_konrad
Repacked DepthArt
321 likes

@marc_krenn
thanks, man! :)
3 likes

@thdxr
cool
116 likes

@RehanAS21
Can you share the link of the code you are using for this video. I want to try it.
71 likes

@reczko_konrad
Sure! I’m building it as a TypeGPU example so it will be fully open and runnable just like my selfie segmentation inference
362 likes

@ryanvogel
woah this is insane wtf holyshit
43 likes

@g0ustalo
can this add dynamic backgrounds in webcam?
30 likes

@reczko_konrad
Yeah, you get raw depth and pixel color you can do whatever you want with it
57 likes

@oprydai
this is sickk
23 likes

@enrub_en
You invented Navi! :)
23 likes

@mrousavy
Does this use the TrueDepth camera? VisionCamera?
22 likes

@reczko_konrad
This on web but I will port it to Vision Camera on RN too
58 likes

@mrousavy
Nice! let me know how it goes, VisionCamera gives you depth frames via the CameraDepthOutput:
6 likes

@reczko_konrad
I actually wanted to run my custom network and just use the external texture interface via react-native-webgpu. Worked nicely for me last time :D
1 like

@mrousavy
wdym exactly? no depth streaming? and which external texture interface do you mean, NativeBuffer?
1 like

@reczko_konrad
Yup, exactly, I just take the raw camera info and run the inference via TypeGPU compute shaders
3 likes




















