SNE-RoadSeg

SNE-RoadSeg copied to clipboard

Hello. I would like to utilize the result of SNE-RoadSeg+ (IROS 2021). However, I could not reproduce your result. Would you give me trained parameter file or code of SNE-RoadSeg+?

MaryAhn

I I want to transform the depth map to disparity map. D=f*b/Z but I don't know b. Do you know? thanks

yanchaocui

Is the label in the R2D dataset a single channel? Or is it a three-channel?

wxyWendy

kitti dataset without validation

1

in kitti, i just find training and testing in download, can you share your dataset with me? just need validation qq:[email protected]. thanks !

yanchaocui

What I understand is that when sne finds the optimal normal direction, it ignores the fluctuations in the xy direction and only optimizes the z direction. Is this understanding correct,...

ghost

epochs

5

(R2D dataset) How many epochs did you train on RoadSeg-152? The default maximum epoch value is 1000. However it is too big size. Thanks.

jiyeooong

Hi, after reading your paper (https://arxiv.org/pdf/2107.14599.pdf) I have a question on SNE-RoadSeg+ you proposed. The solution to the extreme problem in equation (3) is not so trivial. Can you give...

Jiayi719

In the R2D dataset, I read the depth image as an RGB image, and followed the instructions in README to convert the image with 3 channel into depth value, and...

ybWang0820

Testing without depth image input

1

I've generated some depth maps using [Midas](https://github.com/isl-org/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...

cteckwee

About palette.txt

1

Hi, nice work! I'm confused with file palette.txt, can you please explain the usage of this file?

heguohao0728