Rui Li

How to get the error map between predicted depth and the GT depth map

1

Hi, I'm very interested in the error map visualization in Fig.4 of your paper. Do you use the projected LIDAR point cloud as the GT, or the improved ground truth...

Versions of torch and torchvision in the experiment implementation

3

Hi anuragranj, The requirements.txt of your code denotes the necessary packages for your code's implementation. However I encoutered problems when installing the spatial-correlation-sampler, which may be a result of version...

Question about the preparation for the training set

1

Thanks for the impressive work! To train the dataset, I downloaded 2650 Flickr2K HR images and 900 DIV2K_train_HR images, and copy them together to the /traing_path/HR folder. However, when I...

How's the pre-trained semantic segmentation model trained on, Cityscape or KITTI?

4

Hi, Thanks for your solid work and the datasets! As you provided the pre-computed semantic labels for KITTI using method of Zhu _etal_ , I wonder if the semantic segmentation...

Question about the Depth Morph Step.

4

Hi, Thank again for your brilliant work. I am a little confused when I read the Depth Morph part of the paper. In the implementation, what I understand is that...

Share of the Segmentation Results

1

@TWJianNuo Thank you a lot for sharing the code of this brilliant work! We are following your work to conduct semantic augmented depth estimation. Due to the absent of semantic...

Hi Thanks for the great work and the decently-written, well-commented codebase! I noticed you also have GMFlow as an alternative optical flow estimator but the default setting is still RAFT....

Inferior scores of both provided models and trained models

1

Hi Brummi, I tried to evaluate your provided model on the KITTI-raw and KITTI-360 datasets, both yielded suboptimal results 1. KITTI-360 - testing image: The unzipped PNG image (w/o preprocessing)...

Any schedule to release the code?

2

Hey Isabella, Thanks for sharing the great work! Do you have any schedules to release the code? It would be great if you set an approximate time so we can...