Home

Awesome

Real-time intelligent 3D holographic photography for real-world scenarios

Xianlin Song, Jiaqing Dong, Minghao Liu, Zehao Sun, Zibang Zhang, Jianghao Xiong, Zilong Li, Xuan Liu, Qiegen Liu*
Real-time intelligent 3D holographic photography for real-world scenarios
Optics Express Vol. 32, Issue 14, pp. 24540-24552 (2024)
https://doi.org/10.1364/OE.529107

https://github.com/djq-2000/123/assets/56143723/b8c3cbd7-5bac-45f7-ad20-8a40451dd00d

Getting Started

This code runs with Python 3.8.17, Pytorch 2.0.1 and TensorRT 8.6.0

- ./src/

- ./trt/

Training

python ./src/train.py --p_loss --l2_loss --num_epochs 60 --data_path <The address of your training set>

Testing

python predict_rgbd_multiprocess.py

Checkpoints

We provide pretrained checkpoints. The pre-trained models in - ./src/checkpoints/CNN_1024_30/53.pth

Ackonwledgement

We are thankful for the open source of tensor_holography ,HoloEncoder, HoloEncoder-Pytorch-Version and Self-Holo. These works are very helpful for our research.

Other Related Projects