All Projects → wetadigital → Physlight

wetadigital / Physlight

Licence: apache-2.0

Projects that are alternatives of or similar to Physlight

Cubicasa5k
CubiCasa5k floor plan dataset
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Interaction network pytorch
Pytorch Implementation of Interaction Networks for Learning about Objects, Relations and Physics
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Cbe20255
Introduction to Chemical Engineering Analysis
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Python
Source code about Python Development
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Bigdata
NJU Master Course **Big Data Mining and Analysis**
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Estimation Of Remaining Useful Life Using Cnn
Convolutional Neural Network based regression approach for estimating machinery's remaining useful life
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Gde
Graph Neural Ordinary Differential Equations
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Nab
The Numenta Anomaly Benchmark
Stars: ✭ 1,352 (+1265.66%)
Mutual labels:  jupyter-notebook
Keras Gradcam
Keras implementation of GradCAM.
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Scipy 2014 julia
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Hmm
An implementation of the Viterbi Algorithm for training Hidden Markov models. This repo accompanies the video found here: https://www.youtube.com/watch?v=kqSzLo9fenk
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Droneblocks Tello Python
A DroneBlocks course on drone programming with Tello using Python scripts
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Keras Tutorial
Tutorial teaching the basics of Keras and some deep learning concepts
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Dl book
legend
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Objectron
Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes
Stars: ✭ 1,352 (+1265.66%)
Mutual labels:  jupyter-notebook
Mc gradients
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Tf Vs Pytorch
A companion code for my Medium post
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook
Linear algebra with python
Lecture Notes for Linear Algebra Featuring Python
Stars: ✭ 1,355 (+1268.69%)
Mutual labels:  jupyter-notebook
Almond
A Scala kernel for Jupyter
Stars: ✭ 1,354 (+1267.68%)
Mutual labels:  jupyter-notebook
Ds For Telco
Source material for Data Science for Telecom Tutorial at Strata Singapore 2015
Stars: ✭ 98 (-1.01%)
Mutual labels:  jupyter-notebook

PhysLight

This repository contains example materials for Weta Digital's PhysLight system as presented in the Siggraph 2020 Talk PhysLight: An End-to-End Pipeline for Scene-Referred Lighting. Slides can be found here.

teaser image

The imaging notebook shows a simple example of calculating the imaging ratio and checking that it gives the correct response for an idealized camera system.

The data directory contains the spectral sensitivity curves of a number of cameras as measured with our 'lightsaber' system. It also contains a notebook that loads the data and plots the curves for visual inspection.

curves image

The physlight camera model notebook shows how to use the curves to convert from spectral radiance to Camera RGB, solve matrices to go from Camera RGB to XYZ, and compares different approaches for handling white balance.

chart image

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].