Need help with Seeing-Motion-in-the-Dark?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

198 Stars 54 Forks 21 Commits 13 Opened issues


Seeing Motion in the Dark. ICCV19

Services available


Need anything else?

Contributors list

# 13,681
17 commits

Seeing Motion in the Dark

This is a Tensorflow implementation of Seeing Motion in the Dark in ICCV 2019, by Chen Chen, Qifeng Chen, Minh N. Do, and Vladlen Koltun.


Demo Video

Code and Data


Required python (version 2.7) libraries: Tensorflow (1.8.0) + Scipy + Numpy + Rawpy + OpenCV (4.1.0).

Tested in Ubuntu 16.04 + Nvidia Tesla V100 32 GB with Cuda (>=9.0) and CuDNN (>=7.1). CPU mode should also work with minor changes but not tested.

Testing and training the models

To reproduce the results, you only need to download the pre-processed data: long, short, and put them in

. To try the pre-trained model, download the model in

To retrain a new model, run:


To generate the 5th frame of each video, run


To generate the videos, run


By default, the code takes the data in the

and the output folder is

Original sensor raw data

The original raw data is much larger. If you need to process the data in a different way, you can download the camera output raw data here: Part1, Part2, Part3, Part4, Part5 and long.


If you use our code and dataset for research, please cite our paper:

Chen Chen, Qifeng Chen, Minh N. Do, and Vladlen Koltun, "Seeing Motion in the Dark", in ICCV, 2019.


MIT License.


  1. Can I test my own data using the provided model?

The proposed method is designed for sensor raw data. The pretrained model probably not work for data from another camera sensor. We do not have support for other camera data. It also does not work for images after camera ISP, i.e., the JPG or PNG data.

  1. Will this be in any product?

This is a research project and a prototype to prove a concept.

  1. How can I train the model using my own raw data?

Generally, you will need to pre-process your data in a similar way. That is black level subtraction, packing, applying target gain and run some pre-defined temporal filters. The test data should be pre-processed in the same way.

  1. What if my GPU memory is too small to train model?

We provided a
for small memory GPUs. After the training on small resolution, you will need to finetune it on CPU using the
(modify the epoch and learning rate to make it continue training).


If you have addtional questions after reading the FAQ, please email to [email protected]

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.