Testing without depth image input

[cteckwee]

I've generated some depth maps using Midas for non-Kitti images. Then inverted the depth image and feed into SNE-RoadSeg network but the result is hardly usable. Is there a way to segment road without using depth image? The use case is to segment out ground region for arbitrary RGB images only.

[hlwang1124]

Hi, @cteckwee . Sorry for the late response. I suggest you adopt existing single-modal networks. For example, mmsegmentation has provided many existing networks with their pre-trained weights on the Cityscapes dataset.