Papers

Learning Spatiotemporal Features with 3D Convolutional Networks (C3D: Generic Features for Video Analysis)

• project page: http://vlg.cs.dartmouth.edu/c3d/
• arxiv: http://arxiv.org/abs/1412.0767
• slides: http://web.cs.hacettepe.edu.tr/~aykut/classes/spring2016/bil722/slides/w07-conv3d.pdf
• github: https://github.com/facebook/C3D

C3D Model for Keras trained over Sports 1M

• project page: https://imatge.upc.edu/web/resources/c3d-model-keras-trained-over-sports-1m

Sports 1M C3D Network to Keras

• notebook: http://nbviewer.jupyter.org/gist/albertomontesg/d8b21a179c1e6cca0480ebdf292c34d2/Sports1M%20C3D%20Network%20to%20Keras.ipynb

Deep End2End Voxel2Voxel Prediction

• arxiv: http://arxiv.org/abs/1511.06681

Aligning 3D Models to RGB-D Images of Cluttered Scenes

• paper: http://www.cs.berkeley.edu/~rbg/papers/cvpr15/align2rgbd.pdf

Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images

• homepage: http://dss.cs.princeton.edu/
• arxiv: http://arxiv.org/abs/1511.02300

Multi-view 3D Models from Single Images with a Convolutional Network

• arxiv: http://arxiv.org/abs/1511.06702

Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video

• arxiv: http://arxiv.org/abs/1511.09439
• project page: https://fling.seas.upenn.edu/~xiaowz/dynamic/wordpress/monocular-human-pose/
• video: http://weibo.com/p/230444264a8772b7fff71cd23e40b8a88dcaad

RotationNet: Learning Object Classification Using Unsupervised Viewpoint Estimation

• arxiv: http://arxiv.org/abs/1603.06208

DeepContext

DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding

• paper: http://deepcontext.cs.princeton.edu/paper.pdf
• project page: http://deepcontext.cs.princeton.edu/

Volumetric and Multi-View CNNs for Object Classification on 3D Data

• homepage: http://graphics.stanford.edu/projects/3dcnn/
• arxiv: https://arxiv.org/abs/1604.03265
• github: https://github.com/charlesq34/3dcnn.torch

Deep3D

Deep3D: Automatic 2D-to-3D Video Conversion with CNNs

• project page: http://dmlc.ml/mxnet/2016/04/04/deep3d-automatic-2d-to-3d-conversion-with-CNN.html
• paper: http://homes.cs.washington.edu/~jxie/pdf/deep3d.pdf
• github: https://github.com/piiswrong/deep3d

Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

• arxiv: http://arxiv.org/abs/1604.03650

3D-R2N2

3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction

• arxiv: http://arxiv.org/abs/1604.00449
• github: https://github.com/chrischoy/3D-R2N2

Projects

StereoConvNet: Stereo convolutional neural network for depth map prediction from stereo images

• github: https://github.com/LouisFoucard/StereoConvNet