Awesome Open Source
Awesome Open Source

Self-supervised Deep Depth Denoising

Paper Conference Project Page

Created by Vladimiros Sterzentsenko*, Leonidas Saroglou*, Anargyros Chatzitofis*, Spyridon Thermos*, Nikolaos Zioulis*, Alexandros Doumanoglou, Dimitrios Zarpalas, and Petros Daras from the Visual Computing Lab @ CERTH


About this repo

This repo includes the training and evaluation scripts for the fully convolutional autoencoder presented in our paper "Self-Supervised Deep Depth Denoising" (to appear in ICCV 2019). The autoencoder is trained in a self-supervised manner, exploiting RGB-D data captured by Intel RealSense D415 sensors. During inference, the model is used for depthmap denoising, without the need of RGB data.


The code has been tested with the following setup:

  • Pytorch 1.0.1
  • Python 3.7.2
  • CUDA 9.1
  • Visdom

Model Architecture


Encoder: 9 CONV layers, input is downsampled 3 times prior to the latent space, number of channels doubled after each downsampling.

Bottleneck: 2 residual blocks, ELU-CONV-ELU-CONV structure, pre-activation.

Decoder: 9 CONV layers, input is upsampled 3 times using interpolation followed by a CONV layer.


To see the available training parameters:

python -h

Training example:

python --batchsize 2 --epochs 20 --lr 0.00002 --visdom --visdom_iters 500 --disp_iters 10 --train_path /path/to/train/set


The weights of pretrained models can be downloaded from here:

  • ddd --> trained with multi-view supervision (as presented in the paper):
  • ddd_ae --> same model architecture, no multi-view supervision (for comparison purposes)

To denoise a RealSense D415 depth sample using a pretrained model:

python --model_path /path/to/pretrained/model --input_path /path/to/noisy/sample --output_path /path/to/save/denoised/sample

In order to save the input (noisy) and the output (denoised) samples as pointclouds add the following flag to the inference script execution:

--pointclouds True

To denoise a sample using the pretrained autoencoder (same model trained without splatting) add the following flag to the inference script (and make sure you load the "ddd_ae" model):

--autoencoder True

Benchmarking: the mean inference time on a GeForce GTX 1080 GPU is 11ms.


If you use this code and/or models, please cite the following:

  author       = "Vladimiros Sterzentsenko and Leonidas Saroglou and Anargyros Chatzitofis and Spyridon Thermos and Nikolaos Zioulis and Alexandros Doumanoglou and Dimitrios Zarpalas and Petros Daras",
  title        = "Self-Supervised Deep Depth Denoising",
  booktitle    = "ICCV",
  year         = "2019"


Our code is released under MIT License (see LICENSE file for details)

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (53,199
autoencoder (79
self-supervised-learning (58
rgbd (27