testing result is better in RGB format than default BGR format?

[YichengWu]

I am testing the provided model. By default, the input is in BGR format since it uses cv2.imread. I found that if the images are converted to RGB format cv2.COLOR_BGR2RGB, the depth map is even better. I checked the training code, it reads images using cv2.imread. So I am wondering why it is the case. Does the author or anyone else see similar phenomena?