標籤:

deep learning for 3D DATA

Some high-light papers are selected just for reference, most of them are associated with machine learning(deep learning) for 3D data.

From the perspective of 3D data representation:

(1) View-based:

  1. Multi-view Convolutional Neural Networks for 3D Shape Recognition-Hang Su et al. (ICCV 2015)
  2. Multi-view 3D Models from Single Images with a Convolutional Network – Tatarchenko et al. (ECCV 2016)

(2) Voxels-based

  1. Learning Semantic Deformation Flows with 3D Convolutional Networks – Yumer et al. (ECCV 2016)
  2. 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction – Choy et al. (ECCV 2016)
  3. Multi-view Consistency as Supervisory Signal for Learning Shape and Pose Prediction – Tulsiani et al. (CVPR 2018)

(3) Octrees

  1. Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs – Tatarchenko et al. (ICCV 2017)

(4) Volumetric Primitives

  1. Learning Shape Abstractions by Assembling Volumetric Primitives – Tulsiani et al. (CVPR 2017)

(5) Pointclouds (Classification&Segmentation&Matching)

  1. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation – Qi et al. (CVPR 2017 )
  2. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space – Qi et al. (NIPS 2017)
  3. PointCNN – Li et al. (Arxiv 2018)
  4. Frustum PointNets for 3D Object Detection from RGB-D Data – Qi et al. (CVPR 2018)
  5. PU-Net: Point Cloud Upsampling Network – Yu et al. (CVPR 2018)
  6. PPFNet: Global Context Aware Local Features for Robust 3D Point Matching – Deng et al. (CVPR 2018)
  7. Dynamic Graph CNN for Learning on Point Clouds – Wang et al. (Arxiv 2018)
  8. SO-Net: Self-Organizing Network for Point Cloud Analysis-Jiaxin Li.et al. (Arxiv 2018)

(6) Pointclouds (Generative)

  1. PSGN: A Point Set Generation Network for 3D Object Reconstruction from a Single Image – Fan et al. (CVPR 2017)
  2. DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image – Kurenkov et al. (WACV 2018)
  3. Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction – Lin et al. (AAAI 2018 )
  4. Learning Representations and Generative Models for 3D Point Clouds – Achlioptas et al. (ICLR-W 2017)

(7) Mesh

  1. Neural 3D Mesh Renderer – Kato et al. (CVPR 2018)
  2. AtlasNet: A Papier-Maché Approach to Learning 3D Surface Generation – Groueix et al. (CVPR 2018 )

推薦閱讀:

選購一款4k,3d的智能電視,哪個品牌的性價比比較高?
丘成桐的團隊的3D技術具體是什麼?如何理解微分幾何在其中的應用?
類似於這種摺紙3d海報是怎麼做出來的?
為什麼現在3D遊戲風格、顏色都是偏黑暗,沒有色彩明朗、鮮艷的呢?
魔獸世界的裝備外形是如何做到所有種族,性別通吃匹配的?

TAG:3D |