This is a keras and tensorflow implementation of Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation, a CVPR 2019 oral paper.

The repository includes:

• Source code of NOCS.
• Training code
• Detection and evaluation code
• Pre-trained weights

• CAMERA Dataset: Training/Test
• Real Dataset: Training/Test

NOTE: You are required to cite our paper if you use the dataset. The data is only for non-commercial use. Please reach out to us for other use cases.

• Python 3.5
• Tensorflow 1.3.0
• Keras 2.1.5
• cPickle

# Train a new model from pretrained COCO weight
python3 train.py

# Detect using a checkpoint
python3 detect_eval.py --mode detect --ckpt_path=/ckpts/ckpt 

# Evaluate a checkpoint
python3 detect_eval.py --mode eval --ckpt_path=/ckpts/ckpt