SfMLearner

SfMLearner copied to clipboard

converting depth map to Pseudo-color image

1

hello Junj Hu Can you share your code which can be used for converting depth map to Pseudo-color image . I want to compare my depth estimation results with yours...

ITking666

no direct link about "leftImg8bit_sequence_trainvaltest"datasets in cityscapes

4

where should I contact to get download link about "leftImg8bit_sequence_trainvaltest"? in cityscapes ,some datasets have direct link after signing in,but some not? How could I do? thanks.

biexiangduo

Do you have IMU data in KITTI?

1

I'm sorry to ask you something that is not related to SFMLearner, but I hope I can ask you about IMU data. Because My attention is the fuse of IMU...

QQQJG

I saw that you used optical flow to determine the scene is static or not. What was the threshold value you used? Thank you!

abeyang00

Make3d test

1

Thanks for your share of work. Could you please provide codes of testing on Make3d dataset? Thanks very much.

Zealoe

Umeyama alignment and scaling for computing ATE-5

1

Hello, Why is the standard Umeyama algorithm not used for alignment and scaling of 5-frame trajectories when computing the ATE-5?

hemangchawla

GT depth generation

1

Hello, may I ask how the GT depth image in your paper was generated?Kitti seems to have given only sparse depth maps, how to generate a pixel by pixel GT...

hello7623

ONNX Export

1

Can I export the trained model to onnx format? Any guidance or experience?

wanbin-song

predicted output

3

Hi all, It seems strange I use test_kitti_pose.py to test sequence 9 dataset, and it executes well except some warnings, but nothing is generated.  Does anyone can help me...

danbo2

Image Inverse Warping

1

Hello, Thanks for the code, I am not able to understand the pose estimation. Suppose if I consider t and t+1 images, the predicted pose result should be positive in...

madhubabuv