Would it be possible to avoid the conversion to RGB? (This forum thread says it's CPU-only: https://forums.developer.nvidia.com/t/videoconverts-performa...)
Right now SelfieSegmentation is just a thin wrapper around the selfie segmentation solution provided in https://google.github.io/mediapipe. It operates on RGB frames, so that's why I need the conversion. The model inference is also done on the CPU. Interestingly, there is a GPU mediapipe graph available, but I haven't looked into what's needed to use that yet.
And yes, Boxfilter is just a wrapper around opencv's boxfilter. This is probably the lowest hanging fruit that could be moved to use GPU.