A PaddlePaddle version of Neural Renderer, refer to its PyTorch version

Last update: Jul 12, 2022

Overview

Neural 3D Mesh Renderer in PadddlePaddle

A PaddlePaddle version of Neural Renderer, refer to its PyTorch version

Install

Run:

pip install neural-renderer-paddle

Usage

Check examples folder for usage.

Note

Unittest module is not compatiable with PaddlePaddle. If you want to run test, run:

git clone <THIS REPO> neural_renderer_paddle
pip install neural_renderer_paddle/
cd neural_renderer_paddle/tests
python -m unittest test_*.py

Original repo README:

Neural 3D Mesh Renderer (CVPR 2018)

This repo contains a PyTorch implementation of the paper Neural 3D Mesh Renderer by Hiroharu Kato, Yoshitaka Ushiku, and Tatsuya Harada. It is a port of the original Chainer implementation released by the authors. Currently the API is the same as in the original implementation with some smalls additions (e.g. render using a general 3x4 camera matrix, lens distortion coefficients etc.). However it is possible that it will change in the future.

The library is fully functional and it passes all the test cases supplied by the authors of the original library. Detailed documentation will be added in the near future.

Requirements

Python 2.7+ and PyTorch 0.4.0.

The code has been tested only with PyTorch 0.4.0, there are no guarantees that it is compatible with older versions. Currently the library has both Python 3 and Python 2 support.

Note: In some newer PyTorch versions you might see some compilation errors involving AT_ASSERT. In these cases you can use the version of the code that is in the branch at_assert_fix. These changes will be merged into master in the near future.

Installation

You can install the package by running

pip install neural_renderer_pytorch

Since running install.py requires PyTorch, make sure to install PyTorch before running the above command.

Running examples

python ./examples/example1.py
python ./examples/example2.py
python ./examples/example3.py
python ./examples/example4.py

Example 1: Drawing an object from multiple viewpoints

Example 2: Optimizing vertices

Transforming the silhouette of a teapot into a rectangle. The loss function is the difference between the rendered image and the reference image.

Reference image, optimization, and the result.

Example 3: Optimizing textures

Matching the color of a teapot with a reference image.

Reference image, result.

Example 4: Finding camera parameters

The derivative of images with respect to camera pose can be computed through this renderer. In this example the position of the camera is optimized by gradient descent.

From left to right: reference image, initial state, and optimization process.

Citation

@InProceedings{kato2018renderer
    title={Neural 3D Mesh Renderer},
    author={Kato, Hiroharu and Ushiku, Yoshitaka and Harada, Tatsuya},
    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year={2018}
}

You might also like...

Object detection and instance segmentation toolkit based on PaddlePaddle.

A PaddlePaddle version of Neural Renderer, refer to its PyTorch version

Related tags

Overview

Neural 3D Mesh Renderer in PadddlePaddle

Install

Usage

Note

Neural 3D Mesh Renderer (CVPR 2018)

Requirements

Installation

Running examples

Example 1: Drawing an object from multiple viewpoints

Example 2: Optimizing vertices

Example 3: Optimizing textures

Example 4: Finding camera parameters

Citation

You might also like...

Object detection and instance segmentation toolkit based on PaddlePaddle.

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Plaything for Autistic Children (demo for PaddlePaddle/Wechaty/Mixlab project)

Official PaddlePaddle implementation of Paint Transformer

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

Remote sensing change detection tool based on PaddlePaddle

End-to-end image segmentation kit based on PaddlePaddle.

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

Classical OCR DCNN reproduction based on PaddlePaddle framework.

Releases(1.1.3)

1.1.3(Dec 9, 2021)

Owner

AgentMaker

Data-Uncertainty Guided Multi-Phase Learning for Semi-supervised Object Detection

This MVP data web app uses the Streamlit framework and Facebook's Prophet forecasting package to generate a dynamic forecast from your own data.

Continual Learning of Electronic Health Records (EHR).

For IBM Quantum Challenge 2021 (May 20 - 26)

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

NeuroFind - A solution to the to the Task given by the Oberseminar of Messtechnik Institute of TU Dresden in 2021

Parameterising Simulated Annealing for the Travelling Salesman Problem

PyTorch implementation of our paper: Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Look Who’s Talking: Active Speaker Detection in the Wild

Code for the paper "PortraitNet: Real-time portrait segmentation network for mobile device" @ CAD&Graphics2019

Split Variational AutoEncoder

Official PyTorch Implementation for "Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes"

TensorFlow-LiveLessons - "Deep Learning with TensorFlow" LiveLessons

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)

BARTScore: Evaluating Generated Text as Text Generation

The Submission for SIMMC 2.0 Challenge 2021

Training DiffWave using variational method from Variational Diffusion Models.

Single Image Random Dot Stereogram for Tensorflow

TorchFlare is a simple, beginner-friendly, and easy-to-use PyTorch Framework train your models effortlessly.