EdgeDepth

This is the reference PyTorch implementation for training and testing depth estimation models using the method described in

The Edge of Depth: Explicit Constraints between Segmentation and Depth

Shengjie Zhu, Garrick Brazil and Xiaoming Liu

CVPR 2020

⚙️ Setup

Compile Morphing operaiton:

We implement a customized Morphing Operation in our evaluation and training codes. You can still do training and evaluation without it with a sacrifice of performance. To enable it, you can do as follows:
1. Guranttee your computer's cuda version the same as your pytorch cuda version.
2. Type:
```
cd bnmorph
python setup.py install
cd ..
```
You should be able to successfully compile it if you can compile cuda codes in this Pytorch Tutorial
Prepare Kitti Data: We use Kitti Raw Dataset as well as predicted semantics label from this Paper.
1. To download Kitti Raw Data
```
wget -i splits/kitti_archives_to_download.txt -P kitti_data/
```
1. Use thins Link to download precomputed semantics Label

⏳ Training

Training Code will be released soon.

📊 evaluation

Pretrained Model is available here

Precompute GroundTruth DepthMap

python export_gt_depth.py --data_path [Your Kitti Raw Data Address] --split eigen

To Evaluate without using Morphing, use command:

python evaluate_depth.py --split eigen --dataset kitti --data_path [Your Kitti Raw Data Address] --load_weights_folder [Your Model Address] --eval_stereo \
 --num_layers 50 --post_process

To Evaluate using Morphing, use command:

python evaluate_depth.py --split eigen --dataset kitti --data_path [Your Kitti Raw Data Address] --load_weights_folder [Your Model Address] --eval_stereo \
 --num_layers 50 --post_process --bnMorphLoss --load_semantics --seman_path [Your Predicted Semantic Label Address]

You should get performance similar to Entry "Ours" listed in the table:

Method Name Use Lidar Groundtruth? Is morphed? KITTI abs. rel. error delta < 1.25

BTS Yes No 0.091 0.904

Depth Hints No No 0.096 0.890

Ours No No 0.091 0.898

Ours No Yes 0.090 0.899

Method Name	Use Lidar Groundtruth?	Is morphed?	KITTI abs. rel. error	delta < 1.25
BTS	Yes	No	0.091	0.904
Depth Hints	No	No	0.096	0.890
Ours	No	No	0.091	0.898
Ours	No	Yes	0.090	0.899

🖼 Running on your own images

To run on your own images, run:

python test_simple.py --image_path <your_image_path>
  --model_path <your_model_path>
  --num_layers <18 or 50>

This will save depths as a numpy array (in original resolution), and a colormapped depth and disparity image.

Acknowledgment

Quite a few our code base come from Monodepth2 and Depth Hints

qaz670756/EdgeDepth-Release