InverseRenderNet Save

InverseRenderNet: Learning single image inverse rendering, CVPR 2019.

Project README

InverseRenderNet: Learning single image inverse rendering

!! Check out our new work InverseRenderNet++ paper and code, which improves the inverse rendering results and shadow handling.

This is the implementation of the paper "InverseRenderNet: Learning single image inverse rendering". The model is implemented in tensorflow.

If you use our code, please cite the following paper:

    title={InverseRenderNet: Learning single image inverse rendering},
    author={Yu, Ye and Smith, William AP},
    booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},



To run our evaluation code, please create your environment based on following dependencies:

tensorflow 1.12.0
python 3.6

Pretrained model

  • Download our pretrained model from: Link
  • Unzip the downloaded file
  • Make sure the model files are placed in a folder named "irn_model"

Test on demo image

You can perform inverse rendering on random RGB image by our pretrained model. To run the demo code, you need to specify the path to pretrained model, path to RGB image and corresponding mask which masked out sky in the image. The mask can be generated by PSPNet, which you can find on Finally inverse rendering results will be saved to the output folder named by your argument.

python3 --model /PATH/TO/irn_model --image demo.jpg --mask demo_mask.jpg --output test_results

Test on IIW

python3 --model /PATH/TO/irn_model --iiw /PATH/TO/iiw-dataset


Train from scratch

The training for InverseRenderNet contains two stages: pre-train and self-train.

  • To begin with pre-train stage, you need to use training command specifying option -m to pre-train.
  • After finishing pre-train stage, you can run self-train by specifying option -m to self-train.

In addition, you can control the size of batch in training, and the path to training data should be specified.

An example for training command:

python3 -n 2 -p Data -m pre-train

Data for training

To directly use our code for training, you need to pre-process the training data to match the data format as shown in examples in Data folder.

In particular, we pre-process the data before training, such that five images with great overlaps are bundled up into one mini-batch, and images are resized and cropped to a shape of 200 * 200 pixels. Along with input images associated depth maps, camera parameters, sky masks and normal maps are stored in the same mini-batch. For efficiency, every mini-batch containing all training elements for 5 involved images are saved as a pickle file. While training the data feeding thread directly load each mini-batch from corresponding pickle file.

Open Source Agenda is not affiliated with "InverseRenderNet" Project. README Source: YeeU/InverseRenderNet
Open Issues
Last Commit
1 month ago

Open Source Agenda Badge

Open Source Agenda Rating