# TensorFlow Graphics
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Build](https://github.com/tensorflow/graphics/workflows/Build/badge.svg?branch=master)](https://github.com/tensorflow/graphics/actions)
[![Code coverage](https://img.shields.io/coveralls/github/tensorflow/graphics.svg)](https://coveralls.io/github/tensorflow/graphics)
[![PyPI project status](https://img.shields.io/pypi/status/tensorflow-graphics.svg)](https://pypi.org/project/tensorflow-graphics/)
[![Supported Python version](https://img.shields.io/pypi/pyversions/tensorflow-graphics.svg)](https://pypi.org/project/tensorflow-graphics/)
[![PyPI release version](https://img.shields.io/pypi/v/tensorflow-graphics.svg)](https://pypi.org/project/tensorflow-graphics/)
[![Downloads](https://pepy.tech/badge/tensorflow-graphics)](https://pepy.tech/project/tensorflow-graphics)
The last few years have seen a rise in novel differentiable graphics layers
which can be inserted in neural network architectures. From spatial transformers
to differentiable graphics renderers, these new layers leverage the knowledge
acquired over years of computer vision and graphics research to build new and
more efficient network architectures. Explicitly modeling geometric priors and
constraints into neural networks opens up the door to architectures that can be
trained robustly, efficiently, and more importantly, in a self-supervised
fashion.
## Overview
At a high level, a computer graphics pipeline requires a representation of 3D
objects and their absolute positioning in the scene, a description of the
material they are made of, lights and a camera. This scene description is then
interpreted by a renderer to generate a synthetic rendering.
<div align="center">
<img border="0" src="https://storage.googleapis.com/tensorflow-graphics/git/readme/graphics.jpg" width="600">
</div>
In comparison, a computer vision system would start from an image and try to
infer the parameters of the scene. This allows the prediction of which objects
are in the scene, what materials they are made of, and their three-dimensional
position and orientation.
<div align="center">
<img border="0" src="https://storage.googleapis.com/tensorflow-graphics/git/readme/cv.jpg" width="600">
</div>
Training machine learning systems capable of solving these complex 3D vision
tasks most often requires large quantities of data. As labelling data is a
costly and complex process, it is important to have mechanisms to design machine
learning models that can comprehend the three dimensional world while being
trained without much supervision. Combining computer vision and computer
graphics techniques provides a unique opportunity to leverage the vast amounts
of readily available unlabelled data. As illustrated in the image below, this
can, for instance, be achieved using analysis by synthesis where the vision
system extracts the scene parameters and the graphics system renders back an
image based on them. If the rendering matches the original image, the vision
system has accurately extracted the scene parameters. In this setup, computer
vision and computer graphics go hand in hand, forming a single machine learning
system similar to an autoencoder, which can be trained in a self-supervised
manner.
<div align="center">
<img border="0" src="https://storage.googleapis.com/tensorflow-graphics/git/readme/cv_graphics.jpg" width="600">
</div>
Tensorflow Graphics is being developed to help tackle these types of challenges
and to do so, it provides a set of differentiable graphics and geometry layers
(e.g. cameras, reflectance models, spatial transformations, mesh convolutions)
and 3D viewer functionalities (e.g. 3D TensorBoard) that can be used to train
and debug your machine learning models of choice.
## Installing TensorFlow Graphics
See the [install](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/g3doc/install.md)
documentation for instructions on how to install TensorFlow Graphics.
## API Documentation
You can find the API documentation
[here](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/g3doc/api_docs/python/tfg.md).
## Compatibility
TensorFlow Graphics is fully compatible with the latest stable release of
TensorFlow, tf-nightly, and tf-nightly-2.0-preview. All the functions are
compatible with graph and eager execution.
## Debugging
Tensorflow Graphics heavily relies on L2 normalized tensors, as well as having
the inputs to specific function be in a pre-defined range. Checking for all of
this takes cycles, and hence is not activated by default. It is recommended to
turn these checks on during a couple epochs of training to make sure that
everything behaves as expected. This
[page](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/g3doc/debug_mode.md)
provides the instructions to enable these checks.
## Colab tutorials
To help you get started with some of the functionalities provided by TF
Graphics, some Colab notebooks are available below and roughly ordered by
difficulty. These Colabs touch upon a large range of topics including, object
pose estimation, interpolation, object materials, lighting, non-rigid surface
deformation, spherical harmonics, and mesh convolutions.
NOTE: the tutorials are maintained carefully. However, they are not considered
part of the API and they can change at any time without warning. It is not
advised to write code that takes dependency on them.
### Beginner
<div align="center">
<table>
<tr>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/6dof_alignment.ipynb">Object pose estimation</a></th>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/intrinsics_optimization.ipynb">Camera intrinsics optimization</a></th>
</tr>
<tr>
<td align="center">
<a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/6dof_alignment.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/6dof_pose/thumbnail.jpg" width="200" height="200">
</a>
</td>
<td align="center">
<a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/intrinsics_optimization.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/intrinsics/intrinsics_thumbnail.png" width="200" height="200">
</a>
</td>
</tr>
</table>
</div>
### Intermediate
<div align="center">
<table>
<tr>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/interpolation.ipynb">B-spline and slerp interpolation</a></th>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/reflectance.ipynb">Reflectance</a></th>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/non_rigid_deformation.ipynb">Non-rigid surface deformation</a></th>
</tr>
<tr>
<td align="center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/interpolation.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/interpolation/thumbnail.png" width="200" height="200"> </td>
<td align="center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/reflectance.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/reflectance/thumbnail.png" wid
没有合适的资源?快使用搜索试试~ 我知道了~
tensorflow-graphics-2021.12.3.tar.gz
0 下载量 121 浏览量
2024-03-21
12:48:30
上传
评论
收藏 3.86MB GZ 举报
温馨提示
共475个文件
py:333个
md:17个
png:16个
Python库是一组预先编写的代码模块,旨在帮助开发者实现特定的编程任务,无需从零开始编写代码。这些库可以包括各种功能,如数学运算、文件操作、数据分析和网络编程等。Python社区提供了大量的第三方库,如NumPy、Pandas和Requests,极大地丰富了Python的应用领域,从数据科学到Web开发。Python库的丰富性是Python成为最受欢迎的编程语言之一的关键原因之一。这些库不仅为初学者提供了快速入门的途径,而且为经验丰富的开发者提供了强大的工具,以高效率、高质量地完成复杂任务。例如,Matplotlib和Seaborn库在数据可视化领域内非常受欢迎,它们提供了广泛的工具和技术,可以创建高度定制化的图表和图形,帮助数据科学家和分析师在数据探索和结果展示中更有效地传达信息。
资源推荐
资源详情
资源评论
收起资源包目录
tensorflow-graphics-2021.12.3.tar.gz (475个子文件)
.bazelrc 24B
BUILD 1KB
BUILD 857B
rasterizer_op.cc 14KB
rasterize_triangles_impl.cc 13KB
rasterize_triangles_op.cc 7KB
gl_program.cc 6KB
egl_util.cc 5KB
egl_offscreen_context.cc 5KB
rasterizer_with_context.cc 4KB
gl_render_targets.cc 4KB
rasterizer.cc 4KB
gl_shader_storage_buffer.cc 1KB
setup.cfg 38B
all.csv 316B
opensource_only.files 86B
.flake8 581B
.gitignore 65B
.gitmodules 694B
rasterizer.h 11KB
rasterizer_with_context.h 6KB
gl_render_targets.h 6KB
gl_program.h 5KB
egl_offscreen_context.h 4KB
thread_safe_resource_pool.h 4KB
cleanup.h 3KB
rasterize_triangles_impl.h 3KB
macros.h 3KB
gl_shader_storage_buffer.h 3KB
egl_util.h 2KB
ply_data_test0.h5 194KB
ply_data_train1.h5 194KB
ply_data_train0.h5 194KB
ply_data_train2.h5 194KB
ply_data_test1.h5 194KB
MANIFEST.in 42B
pytest.ini 81B
spherical_harmonics_approximation.ipynb 26KB
mesh_segmentation_demo.ipynb 26KB
6dof_alignment.ipynb 25KB
inverse_rendering.ipynb 22KB
spherical_harmonics_optimization.ipynb 18KB
intrinsics_optimization.ipynb 18KB
demo.ipynb 17KB
matting.ipynb 16KB
train.ipynb 16KB
TFG_tiny_nerf.ipynb 14KB
reflectance.ipynb 14KB
non_rigid_deformation.ipynb 12KB
interpolation.ipynb 11KB
_index.ipynb 5KB
mesh-viewer.js 14KB
array-buffer-data-provider.js 7KB
taxonomy.json 10KB
pix3d.json 9KB
dataset_info.json 3KB
LICENSE 11KB
LICENSE 11KB
cube.mat 32KB
voxel.mat 9KB
voxel.mat 9KB
README.md 13KB
CONTRIBUTING.md 10KB
README.md 5KB
README.md 5KB
README.md 5KB
tensorboard.md 4KB
README.md 3KB
overview.md 3KB
README.md 3KB
README.md 2KB
readme.md 2KB
install.md 1KB
README.md 983B
README.md 955B
debug_mode.md 946B
README.md 641B
README.md 122B
malm_bed_2_obj0_object.mtl 304B
malm_bed_3_obj0_object.mtl 304B
pix3d_train.npy 60KB
pix3d_test.npy 19KB
pix3d_train.npy 144B
pix3d_test.npy 136B
model.obj 22KB
model.obj 22KB
model_normalized.obj 580B
model_normalized.obj 338B
model_normalized.obj 297B
cube.obj 290B
model_normalized.obj 185B
model_normalized.obj 131B
PKG-INFO 675B
PKG-INFO 675B
0010.png 1.17MB
0002.png 952KB
0001.png 164KB
Unlit_Cube_0_0.png 48KB
Unlit_Cube_0_1.png 38KB
Simple_Triangle.png 17KB
共 475 条
- 1
- 2
- 3
- 4
- 5
资源评论
程序员Chino的日记
- 粉丝: 2837
- 资源: 3万+
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- IMG_0694.GIF
- 基于图像的三维模型重建C++源代码+文档说明(高分课程设计)
- 基于聚焦法的工件立体测量方案,根据数据进行三维重建 使用HALCON处理图像,MATLAB拟合数据+源代码+数据集+效果图
- 锄战三国村 修改:货币使用不减 v1.10(2) 原创 (中文).apk
- 基于python实现的单目双目视觉三维重建+源代码+图像图片(高分课程设计)
- 基于C+++OPENCV的全景图像拼接源码(课程设计)
- 基于Python+OpenCV对多张图片进行全景图像拼接,消除鬼影,消除裂缝+源代码+文档说明+界面截图(高分课程设计)
- 基于C++实现的全景图像拼接源码(课程设计)
- 基于SIFT特征点提取和RASIC算法实现全景图像拼接python源码+文档说明+界面截图+详细注释(95分以上课程大作业)
- 基于matlab实现眼部判别的疲劳检测系统+源代码+全部数据+文档说明+详细注释+使用说明+截图(高分课程设计)
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功