I am a participant of the challenge, I am doubtful about the evaluation:
the description of the evaluation as follows:
The evaluation consists from the comparison of the synthesized Bokeh images with the ground truth Bokeh images.
For the Track 1 we use the Mean Opinion Score (MOS) for perceptual quality and the runtime on CPU.
For the Track 2 we use the Mean Opinion Score (MOS) for perceptual quality and the runtime on smartphone GPU.
I wanna know the trad-off of the perceptual quality and the runtime , Which index has higher weight and how is the weight calculated。
Looking forward to your reply。Posted by: MingQian @ May 26, 2020, 6:09 a.m.