Implementation of Nalbach et al. 2017 paper.

Last update: Sep 08, 2022

Overview

Deep Shading

Convolutional Neural Networks for Screen-Space Shading

Our project is based on Nalbach et al. 2017 paper. In this project, a set of buffers are provided to a Deep Convolutional Network in order to synthetize differend shading effects (such as Ambient Occlusion, Depth of Field, Global Illumination and Sub-surface Scattering). The set of buffers depends os the shading effect we want to synthetize.

Input Bufers:

Result (Ambient Occlusion):

Requirements for the project

Python 3.x
Tensorflow 1.10
Keras
OpenCV 3.4(for loading,resizing images)
h5py(for saving trained model)
pyexr

Steps to run the repo

Clone the repo
Download the dataset (http://deep-shading-datasets.mpi-inf.mpg.de/)
Install the requirements
Generate the .tfrecord for trainning and validation (Use the DataReader.py)
Run "Shading.py"

References

[1] Oliver Nalbach, Elena Arabadzhiyska, Dushyant Mehta, Hans-Peter Seidel, Tobias Ritschel Deep Shading: Convolutional Neural Networks for Screen-Space Shading to appear in Proc. EGSR 2017

Implementation of Nalbach et al. 2017 paper.

Related tags

Overview

Deep Shading

Convolutional Neural Networks for Screen-Space Shading

Requirements for the project

Steps to run the repo

References

Owner

Marcel Santana

Measuring if attention is explanation with ROAR

A rough implementation of the paper "A Steering Algorithm for Redirected Walking Using Reinforcement Learning"

Viperdb - A tiny log-structured key-value database written in pure Python

Intrusion Detection System using ensemble learning (machine learning)

Simple helper library to convert a collection of numpy data to tfrecord, and build a tensorflow dataset from the tfrecord.

My usage of Real-ESRGAN to upscale anime, some test and results in the test_img folder

Code for Deep Single-image Portrait Image Relighting

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

Code for "Searching for Efficient Multi-Stage Vision Transformers"

GEP (GDB Enhanced Prompt) - a GDB plug-in for GDB command prompt with fzf history search, fish-like autosuggestions, auto-completion with floating window, partial string matching in history, and more!

Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

Unofficial Alias-Free GAN implementation. Based on rosinality's version with expanded training and inference options.

Deep deconfounded recommender (Deep-Deconf) for paper "Deep causal reasoning for recommendations"

Ensemble Learning Priors Driven Deep Unfolding for Scalable Snapshot Compressive Imaging [PyTorch]

Code for the CVPR 2021 paper: Understanding Failures of Deep Networks via Robust Feature Extraction

A general framework for deep learning experiments under PyTorch based on pytorch-lightning

This is the research repository for Vid2Doppler: Synthesizing Doppler Radar Data from Videos for Training Privacy-Preserving Activity Recognition.

A PyTorch-centric hybrid classical-quantum machine learning framework

Photographic Image Synthesis with Cascaded Refinement Networks - Pytorch Implementation

This is the official repository for our paper: ''Pruning Self-attentions into Convolutional Layers in Single Path''.