Datasets for new state-of-the-art challenge in disentanglement learning

Overview

High resolution disentanglement datasets

This repository contains the Falcor3D and Isaac3D datasets, which present a state-of-the-art challenge for controllable generation in terms of image resolution, photorealism, and richness of style factors, as compared to existing disentanglement datasets.

Falor3D

The Falcor3D dataset consists of 233,280 images based on the 3D scene of a living room, where each image has a resolution of 1024x1024. The meta code corresponds to all possible combinations of 7 factors of variation:

  • lighting_intensity (5)
  • lighting_x-dir (6)
  • lighting_y-dir (6)
  • lighting_z-dir (6)
  • camera_x-pos (6)
  • camera_y-pos (6)
  • camera_z-pos (6)

Note that the number m behind each factor represents that the factor has m possible values, uniformly sampled in the normalized range of variations [0, 1].

Each image has as filename padded_index.png where

index = lighting_intensity * 46656 + lighting_x-dir * 7776 + lighting_y-dir * 1296 + 
lighting_z-dir * 216 + camera_x-pos * 36 + camera_y-pos * 6 + camera_z-pos

padded_index = index padded with zeros such that it has 6 digits.

To see the Falcor3D images by varying each factor of variation individually, you can run

python dataset_demo.py --dataset Falor3D

and the results are saved in the examples/falcor3d_samples folder.

You can also check out the Falcor3D images here: falcor3d_samples_demo, which includes all the ground-truth latent traversals.

Isaac3D

The Isaac3D dataset consists of 737,280 images, based on the 3D scene of a kitchen, where each image has a resolution of 512x512. The meta code corresponds to all possible combinations of 9 factors of variation:

  • object_shape (3)
  • object_scale (4)
  • camera_height (4)
  • robot_x-movement (8)
  • robot_y-movement (5)
  • lighting_intensity (4)
  • lighting_y-dir (6)
  • object_color (4)
  • wall_color (4)

Similarly, the number m behind each factor represents that the factor has m possible values, uniformly sampled in the normalized range of variations [0, 1].

Each image has as filename padded_index.png where

index = object_shape * 245760 + object_scale * 30720 + camera_height * 6144 + 
robot_x-movement * 1536 + robot_y-movement * 384 + lighting_intensity * 96 + 
lighting_y-dir * 16 + object_color * 4 + wall color

padded_index = index padded with zeros such that it has 6 digits.

To see the Isaac3D images by varying each factor of variation individually, you can run

python dataset_demo.py --dataset Isaac3D

and the results are saved in the examples/isaac3d_samples folder.

You can also check out the Isaac3D images here: isaac3d_samples_demo, which includes all the ground-truth latent traversals.

Links to datasets

The two datasets can be downloaded from Google Drive:

  • Falcor3D (98 GB): link
  • Isaac3D (190 GB): link

Besides, we also provide a downsampled version (resolution 128x128) of the two datasets:

  • Falcor3D_128x128 (3.7 GB): link
  • Isaac3D_128x128 (13 GB): link

License

This work is licensed under a Creative Commons Attribution 4.0 International License by NVIDIA Corporation (https://creativecommons.org/licenses/by/4.0/).

You might also like...
LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models
LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models

LaneDet is an open source lane detection toolbox based on PyTorch that aims to pull together a wide variety of state-of-the-art lane detection models. Developers can reproduce these SOTA methods and build their own methods.

Deep Text Search is an AI-powered multilingual text search and recommendation engine with state-of-the-art transformer-based multilingual text embedding (50+ languages).
Deep Text Search is an AI-powered multilingual text search and recommendation engine with state-of-the-art transformer-based multilingual text embedding (50+ languages).

Deep Text Search - AI Based Text Search & Recommendation System Deep Text Search is an AI-powered multilingual text search and recommendation engine w

State-of-the-art data augmentation search algorithms in PyTorch
State-of-the-art data augmentation search algorithms in PyTorch

MuarAugment Description MuarAugment is a package providing the easiest way to a state-of-the-art data augmentation pipeline. How to use You can instal

This is the unofficial code of  Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data
A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)

A selection of State Of The Art research papers (and code) on human trajectory prediction (forecasting). Papers marked with [W] are workshop papers.

FastReID is a research platform that implements state-of-the-art re-identification algorithms.
FastReID is a research platform that implements state-of-the-art re-identification algorithms.

FastReID is a research platform that implements state-of-the-art re-identification algorithms.

Summary Explorer is a tool to visually explore the state-of-the-art in text summarization.
Summary Explorer is a tool to visually explore the state-of-the-art in text summarization.

Summary Explorer Summary Explorer is a tool to visually inspect the summaries from several state-of-the-art neural summarization models across multipl

PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

PaddlePaddle Vision Transformers State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 🤖 PaddlePaddle Visual Transformers (PaddleViT or

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.
🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

English | 简体中文 | 繁體中文 State-of-the-art Natural Language Processing for Jax, PyTorch and TensorFlow 🤗 Transformers provides thousands of pretrained mo

Owner
NVIDIA Research Projects
NVIDIA Research Projects
deep-table implements various state-of-the-art deep learning and self-supervised learning algorithms for tabular data using PyTorch.

deep-table implements various state-of-the-art deep learning and self-supervised learning algorithms for tabular data using PyTorch.

null 63 Oct 17, 2022
State of the Art Neural Networks for Deep Learning

pyradox This python library helps you with implementing various state of the art neural networks in a totally customizable fashion using Tensorflow 2

Ritvik Rastogi 60 May 29, 2022
QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

QuickAI is a Python library that makes it extremely easy to experiment with state-of-the-art Machine Learning models.

null 152 Jan 2, 2023
tsai is an open-source deep learning package built on top of Pytorch & fastai focused on state-of-the-art techniques for time series classification, regression and forecasting.

Time series Timeseries Deep Learning Pytorch fastai - State-of-the-art Deep Learning with Time Series and Sequences in Pytorch / fastai

timeseriesAI 2.8k Jan 8, 2023
😇A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc

------ Update September 2018 ------ It's been a year since TorchMoji and DeepMoji were released. We're trying to understand how it's being used such t

Hugging Face 865 Dec 24, 2022
Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning

Here is deepparse. Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning. Use deepparse to Use the pr

GRAAL/GRAIL 192 Dec 20, 2022
ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a large-scale learning-from-demonstrations benchmark for object manipulation.

ManiSkill-Learn ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge, a large-scale learning-from-dem

Hao Su's Lab, UCSD 48 Dec 30, 2022
Code for paper "A Critical Assessment of State-of-the-Art in Entity Alignment" (https://arxiv.org/abs/2010.16314)

A Critical Assessment of State-of-the-Art in Entity Alignment This repository contains the source code for the paper A Critical Assessment of State-of

Max Berrendorf 16 Oct 14, 2022
Quickly comparing your image classification models with the state-of-the-art models (such as DenseNet, ResNet, ...)

Image Classification Project Killer in PyTorch This repo is designed for those who want to start their experiments two days before the deadline and ki

null 349 Dec 8, 2022
State of the art Semantic Sentence Embeddings

Contrastive Tension State of the art Semantic Sentence Embeddings Published Paper · Huggingface Models · Report Bug Overview This is the official code

Fredrik Carlsson 88 Dec 30, 2022