This is a unified codebase for NN-based monocular depth estimation, the framework is based on detectron2 (with a lot of modifications) and supports both supervised and self-supervised monocular depth estimation methods. The main goal for developing this repository is to help understand popular depth estimation papers, I tried my best to keep the code simple.

• Add unsupervised motion learning

• Add waymo dataset support

1. clone this repo

   SDE_ROOT=/path/to/SimpleDepthEstimation
   git clone https://github.com/zzzxxxttt/SimpleDepthEstimation $SDE_ROOT
   cd $SDE_ROOT

2. create a new conda environment and activate it

   conda create -n sde python=3.7 
   conda activate sde

3. install torch==1.8.0 and torchvision==0.9.0 follow the official instructions. (I haven't tried other pytorch versions)
4. install other requirements

   pip install -r requirements.txt

5. to use waymo dataset, compile waymo-open-dataset according to the official instructions.

1. Download and extract KITTI raw dataset, refined KITTI depth groundtruth, and eigen split files
2. Modify the data path in the config file

1. Download Waymo tfrecords
2. Extract image and depth from tfrecords

   python tools/extract_waymo_data.py --src_dir path/to/tfrecords --dst_dir path/to/extracted/data --split training
   python tools/extract_waymo_data.py --src_dir path/to/tfrecords --dst_dir path/to/extracted/data --split validation

3. Modify the data path in the config file

python path/to/project/train.py --num-gpus 2 --cfg path/to/config RUN_NAME run_name

python path/to/project/train.py --num-gpus 2 --cfg path/to/config --eval MODEL.WEIGHTS /path/to/checkpoint_file

python tools/demo.py --cfg path/to/config --input path/to/image --output path/to/output_dir MODEL.WEIGHTS /path/to/checkpoint_file

visualization:

• add PackNet
• add Dynamic Motion Learning (I have implemented it but still buggy, help welcome!)
• add Depth From Videos in the Wild
• add Full Surround Monodepth
• support more datasets

• detectron2
• Digging into Self-Supervised Monocular Depth Prediction
• From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation
• 3D Packing for Self-Supervised Monocular Depth Estimation
• Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras
• Unsupervised Monocular Depth and Motion Learning