This repository is the official implementation of the TSOHNMEA. The project report can be viewed using this link. Complete end-to-end pipeline code is not included yet.
To install requirements:
pip install -r requirements.txt
As the end-to-end pipeline code is not included, users must manually take the output from each .ipynb section. The order to extracts and input the outputs is
- background_occlusion_handler.ipynb (not included yet, so we suggest to use an image without any background to test the rest of the pipeline)
- Real_ESRGAN_blur_occlusion.ipynb
- PiFUHD_normal_map_estimation.ipynb
- ORDINARY NORMAL MAP ESTIMATION USING PIFU-HD MODEL:
PIFU-HD.mp4
- OUR TRI-STAGE OCCLUSION HANDLING NORMAL MAP ESTIMATION PIPELINE:
Background, Shadow and Blur occlusion of the original input image is handled and the preprocessed input image is sent to the normal map estimation model
Our-pipeline.mp4
- Upload complete end-to-end pipeline code (not included right now because further improvements are being made).
- Include background occlusion handler code (not included right now because more advanced and better architectures are being explored).
- Handle object occlusion.
https://github.com/tensorflow/models/tree/master/research/deeplab
https://github.com/xinntao/Real-ESRGAN
https://github.com/facebookresearch/pifuhd
For any queries, feel free to contact at [email protected].