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

Merge pull request #14 from angeladai/patch 

add shape and scene completion/understanding
master
Yuxuan (Tim) Zhang 2018-04-15 09:13:19 -04:00 committed by GitHub
parent 060c672872 59628c2e5f
commit aa1ea43957
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 13 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@ -108,7 +108,7 @@ To see a survey of RGBD datasets, check out Michael Firman's [collection](http:/
<b>ScanNet (2017)</b> [[Link]](http://www.scan-net.org/)
<br>An RGB-D video dataset containing 2.5 million views in more than 1500 scans, annotated with 3D camera poses, surface reconstructions, and instance-level semantic segmentations.
<p align="center"><img width="50%" src="http://www.scan-net.org/img/voxel-predictions.jpg" /></p>
<p align="center"><img width="50%" src="http://www.scan-net.org/img/annotations.png" /></p>
<b>Matterport3D: Learning from RGB-D Data in Indoor Environments (2017)</b> [[Link]](https://niessner.github.io/Matterport/)
<br>10,800 panoramic views (in both RGB and depth) from 194,400 RGB-D images of 90 building-scale scenes of private rooms. Instance-level semantic segmentations are provided for region (living room, kitchen) and object (sofa, TV) categories.
@ -288,6 +288,9 @@ To see a survey of RGBD datasets, check out Michael Firman's [collection](http:/
<b>Learning Hierarchical Shape Segmentation and Labeling from Online Repositories (2017)</b> [[Paper]](http://cs.stanford.edu/~ericyi/project_page/hier_seg/index.html)
<p align="center"><img width="50%" src="http://cs.stanford.edu/~ericyi/project_page/hier_seg/figures/teaser.jpg" /></p>
:space_invader: <b>ScanNet (2017)</b> [[Paper]](https://arxiv.org/pdf/1702.04405.pdf) [[Code]](https://github.com/scannet/scannet)
<p align="center"><img width="50%" src="http://www.scan-net.org/img/voxel-predictions.jpg" /></p>
:game_die: <b>PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (2017)</b> [[Paper]](http://stanford.edu/~rqi/pointnet/) [[Code]](https://github.com/charlesq34/pointnet)
<p align="center"><img width="40%" src="https://web.stanford.edu/~rqi/papers/pointnet.png" /></p>
@ -316,6 +319,9 @@ Parsing of Large-scale 3D Point Clouds (2017)</b> [[Paper]](https://arxiv.org/pd
:game_die: <b>PointCNN (2018)</b> [[Paper]](https://yangyanli.github.io/PointCNN/)
<p align="center"><img width="50%" src="http://yangyan.li/images/paper/pointcnn.png" /></p>
:camera::space_invader: <b>3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation (2018)</b> [[Paper]](https://arxiv.org/pdf/1803.10409.pdf)
<p align="center"><img width="50%" src="https://cs.stanford.edu/~adai/papers/2018/1threedmv/teaser.jpg" /></p>
<a name="3d_synthesis" />
## 3D Model Synthesis/Reconstruction
@ -438,6 +444,9 @@ _Deep Learning Methods_
: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) [[Code]](https://github.com/Amir-Arsalan/Synthesize3DviaDepthOrSil)
<p align="center"><img width="50%" src="https://jiajunwu.com/images/spotlight_3dvae.jpg" /></p>
:space_invader: <b>Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis (2017)</b> [[Paper]](https://arxiv.org/pdf/1612.00101.pdf) [[Code]](https://github.com/angeladai/cnncomplete)
<p align="center"><img width="50%" src="http://graphics.stanford.edu/projects/cnncomplete/teaser.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) [[Code]](https://github.com/lmb-freiburg/ogn)
<p align="center"><img width="50%" src="https://ai2-s2-public.s3.amazonaws.com/figures/2016-11-08/6c2a292bb018a8742cbb0bbc5e23dd0a454ffe3a/2-Figure2-1.png" /></p>
@ -647,3 +656,6 @@ _Deep Learning Methods_
<b>PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image (2018 CVPR)</b> [[Paper]](http://art-programmer.github.io/planenet/paper.pdf) [[Code]](http://art-programmer.github.io/planenet.html)
<p align="center"><img width="50%" src="http://art-programmer.github.io/images/planenet.png" /></p>
:space_invader: <b>ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans (2018)</b> [[Paper]](https://arxiv.org/pdf/1712.10215.pdf)
<p align="center"><img width="50%" src="https://cs.stanford.edu/~adai/papers/2018/0scancomplete/teaser.jpg" /></p>