Inference
/
3D-Machine-Learning
mirror of https://github.com/Xianpeng919/3D-Machine-Learning.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update README.md

master
Yuxuan (Tim) Zhang 2017-08-14 23:25:28 -04:00 committed by GitHub
parent 5720de3027
commit e1ad9c7476
1 changed files with 52 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

62
README.md
View File

@ -24,26 +24,25 @@ To make it a collaborative project, you may add content throught pull requests o
To see a survey of RGBD datasets, I recommend to check out Michael Firman's [collection](http://www0.cs.ucl.ac.uk/staff/M.Firman//RGBDdatasets/) as well as the associated paper, [RGBD Datasets: Past, Present and Future](https://arxiv.org/pdf/1604.00999.pdf). Point Cloud Library also has a good dataset [catalogue](http://pointclouds.org/media/).
## Single Object Classification
aaa
to be added
## Multiple Objects Detection
aaa
to be added
## Part Segmentation
aaa
to be added
## 3D Synthesis/Reconstruction
aaa
_Parametric Morphable Model-based methods_
## 3D Style Transfer
### Parametric Morphable Model-based methods
<b>A Morphable Model For The Synthesis Of 3D Faces (1999)</b> [[Paper]](http://gravis.dmi.unibas.ch/publications/Sigg99/morphmod2.pdf)[[Github]](https://github.com/MichaelMure/3DMM)
<p align="center"><img width="50%" src="http://mblogthumb3.phinf.naver.net/MjAxNzAzMTdfMjcz/MDAxNDg5NzE3MzU0ODI3.9lQioLxwoGmtoIVXX9sbVOzhezoqgKMKiTovBnbUFN0g.sXN5tG4Kohgk7OJEtPnux-mv7OAoXVxxCyo3SGZMc6Yg.PNG.atelierjpro/031717_0222_DataDrivenS4.png?type=w420" /></p>
<b>The Space of Human Body Shapes: Reconstruction and Parameterization from Range Scans (2003)</b> [[Paper]](http://grail.cs.washington.edu/projects/digital-human/pub/allen03space-submit.pdf)
<p align="center"><img width="50%" src="https://ai2-s2-public.s3.amazonaws.com/figures/2016-11-08/46d39b0e21ae956e4bcb7a789f92be480d45ee12/7-Figure10-1.png" /></p>
### Part-based Template Learning methods
_Part-based Template Learning methods_
<b>Modeling by Example (2004)</b> [[Paper]](http://www.cs.princeton.edu/~funk/sig04a.pdf)
<p align="center"><img width="20%" src="http://gfx.cs.princeton.edu/pubs/Funkhouser_2004_MBE/chair.jpg" /></p>
@ -87,11 +86,54 @@ aaa
<p align="center"><img width="30%" src="https://github.com/timzhang642/test1/blob/master/imgs/Interchangeable%20Components%20for%20Hands-On%20Assembly%20Based%20Modeling.png" /></p>
<b>Shape Completion from a Single RGBD Image (2016)</b> [[Paper]](http://www.kunzhou.net/2016/shapecompletion-tvcg16.pdf)
<p align="center"><img width="30%" src="http://tianjiashao.com/Images/2015/completion.jpg" /></p>
<p align="center"><img width="40%" src="http://tianjiashao.com/Images/2015/completion.jpg" /></p>
### Deep Learning Methods
_Deep Learning Methods_
:camera: <b>Learning to Generate Chairs, Tables and Cars with Convolutional Networks (2014)</b> [[Paper]](https://arxiv.org/pdf/1411.5928.pdf)
<p align="center"><img width="50%" src="https://zo7.github.io/img/2016-09-25-generating-faces/chairs-model.png" /></p>
:game_die: <b>Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces (2015)</b> [[Paper]](https://people.cs.umass.edu/~hbhuang/publications/bsm/)
<p align="center"><img width="50%" src="https://people.cs.umass.edu/~hbhuang/publications/bsm/bsm_teaser.jpg" /></p>
:camera: <b>Multi-view 3D Models from Single Images with a Convolutional Network (2016)</b> [[Paper]](https://arxiv.org/pdf/1511.06702.pdf) [[Code]](https://github.com/lmb-freiburg/mv3d)
<p align="center"><img width="50%" src="https://ai2-s2-public.s3.amazonaws.com/figures/2016-11-08/3d7ca5ad34f23a5fab16e73e287d1a059dc7ef9a/4-Figure2-1.png" /></p>
<p align="center"><img width="40%" src="imgs/a.jpg" /></p>
:camera: <b>View Synthesis by Appearance Flow (2016)</b> [[Paper]](https://people.eecs.berkeley.edu/~tinghuiz/papers/eccv16_appflow.pdf) [[Code]](https://github.com/tinghuiz/appearance-flow)
<p align="center"><img width="50%" src="https://ai2-s2-public.s3.amazonaws.com/figures/2016-11-08/12280506dc8b5c3ca2db29fc3be694d9a8bef48c/6-Figure2-1.png" /></p>
:space_invader: <b>Voxlets: Structured Prediction of Unobserved Voxels From a Single Depth Image (2016)</b> [[Paper]](http://visual.cs.ucl.ac.uk/pubs/depthPrediction/http://visual.cs.ucl.ac.uk/pubs/depthPrediction/)
<p align="center"><img width="50%" src="https://i.ytimg.com/vi/1wy4y2GWD5o/maxresdefault.jpg" /></p>
:space_invader: <b>3D-R2N2: 3D Recurrent Reconstruction Neural Network (2016)</b> [[Paper]](http://cvgl.stanford.edu/3d-r2n2/)
<p align="center"><img width="50%" src="http://3d-r2n2.stanford.edu/imgs/overview.png" /></p>
:space_invader: <b>TL-Embedding Network: Learning a Predictable and Generative Vector Representation for Objects (2016)</b> [[Paper]](https://arxiv.org/pdf/1603.08637.pdf)
<p align="center"><img width="50%" src="https://rohitgirdhar.github.io/GenerativePredictableVoxels/assets/webteaser.jpg" /></p>
:space_invader: <b>3D GAN: Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (2016)</b> [[Paper]](https://arxiv.org/pdf/1610.07584.pdf)
<p align="center"><img width="50%" src="http://3dgan.csail.mit.edu/images/model.jpg" /></p>
:camera: <b>Unsupervised Learning of 3D Structure from Images (2016)</b> [[Paper]](https://arxiv.org/pdf/1607.00662.pdf)
<p align="center"><img width="50%" src="https://adriancolyer.files.wordpress.com/2016/12/unsupervised-3d-fig-10.jpeg?w=600" /></p>
:camera: <b>Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency (2017)</b> [[Paper]](https://shubhtuls.github.io/drc/)
<p align="center"><img width="50%" src="https://shubhtuls.github.io/drc/resources/images/teaserChair.png" /></p>
:camera: <b>Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes with Deep Generative Networks (2017)</b> [[Paper]](http://openaccess.thecvf.com/content_cvpr_2017/papers/Soltani_Synthesizing_3D_Shapes_CVPR_2017_paper.pdf)
<p align="center"><img width="50%" src="https://jiajunwu.com/images/spotlight_3dvae.jpg" /></p>
:space_invader: <b>Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs (2017)</b> [[Paper]](https://arxiv.org/pdf/1703.09438.pdf)
<p align="center"><img width="50%" src="https://ai2-s2-public.s3.amazonaws.com/figures/2016-11-08/6c2a292bb018a8742cbb0bbc5e23dd0a454ffe3a/2-Figure2-1.png" /></p>
:game_die: <b>A Point Set Generation Network for 3D Object Reconstruction from a Single Image (2017)</b> [[Paper]](http://ai.stanford.edu/~haosu/papers/SI2PC_arxiv_submit.pdf)
<p align="center"><img width="50%" src="http://gting.me/2017/07/17/pr-point-set-generation-from-single-image/ps3d_introduction.PNG" /></p>
:camera: <b>Transformation-Grounded Image Generation Network for Novel 3D View Synthesis (2017)</b> [[Paper]](http://www.cs.unc.edu/~eunbyung/tvsn/)
<p align="center"><img width="50%" src="https://eng.ucmerced.edu/people/jyang44/pics/view_synthesis.gif" /></p>
:space_invader: <b>Interactive 3D Modeling with a Generative Adversarial Network (2017)</b> [[Paper]](https://arxiv.org/pdf/1706.05170.pdf)
<p align="center"><img width="50%" src="https://pbs.twimg.com/media/DCsPKLqXoAEBd-V.jpg" /></p>
## 3D Style Transfer
to be added