Disney SIGGRAPH Sampling Based Scene Space Video Processing - ON BLENDER !!!

[GottfriedHofmann]

@BeerBaron

The whole point of the algorithm is the “scene space” processing. The input to the algorithm requires a depth map, which could come from various sources. In the paper they mention that they used both multi-view stereo reconstruction and a Kinect to acquire the footage used for demonstration. None of what you have seen was achieved with just a single camera.

You do not need multiple cameras if you use a video as input for multi-view stereo.

[BeerBaron]

@GottfriedHofmann

You do not need multiple cameras if you use a video as input for multi-view stereo.

That can work for certain kinds of footage of a static scene, but obviously not for a scene with moving actors.

[enilnacs]

@BeerBaron

That can work for certain kinds of footage of a static scene, but obviously not for a scene with moving actors.

which BTW is totally irrelevant for some processes like denoise, or deblur for ex. where no kinekt was used and there are a LOT of moving people.