DIPTE / Deep-Geometry-Learning-Paper

Deep Geometry Learning on Colab

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Deep-Geometry-Learning-Paper

  • πŸ˜„ View-Based
  • πŸ˜† Volume-Based
  • πŸ˜ƒ Point Cloud-Based
  • πŸ˜‰ Mesh-Based
  • πŸ˜‹ Octree-Based
  • 😝 Fusion-Based
  • πŸ˜‚ Datasets

- View-Based


2015

  • [ICCV] Multi-view convolutional neural networks for 3D shape recognition. [tensorflow][pytorch] [Classification. Retrieval. ] πŸ”₯ ⭐
  • [IEEE SIGNAL PROCESSING LETTERS] DeepPano: deep panoramic representation for 3-D shape recognition. [Classification.]

2016

  • [CVPR] GIFT: A Real-time and Scalable 3D Shape Search Engine. [Retrieval.]
  • [ECCV] Deep learning 3D shape surfaces using geometry images. [Classification. Retrieval.]
  • [CVPR] Pairwise decomposition of image sequences for active multi-view recognition. [Classification. Retrieval.]
  • [CVPR] Volumetric and multi-view CNNs for object classification on 3D data. [lua] [Classification. Retrieval.]
  • [arXiv] FusionNet: 3D object classification using multiple data representations. [Classification.]

2017

  • [BMVC] Dominant set clustering and pooling for multi-view 3D object recognition. [MATLAB] [Classification.]
  • [IGTA] Boosting multi-view convolutional neural networks for 3D object recognition via view saliency. [Classification.]
  • [3DOR] Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval. [Classification. Retrieval.]

2018

  • [IEEE TRANSACTION ON MULTIMEDIA] Learning Multi-view Representation with LSTM for 3D Shape Recognition and Retrieval. [Classification. Retrieval.]
  • [IEEE Transactions on Image Processing] SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN with Attention. [Classification. Retrieval.]
  • [CVPR] GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition. [tensorflow] [pytorch][Classification. Retrieval.] πŸ”₯ ⭐
  • [CVPR] Rotationnet: Joint object categorization and pose estimation using multiviews from unsupervised viewpoints. [tensorflow] [pytorch][Classification. Retrieval.] πŸ”₯ ⭐
  • [CVPR] Multi-view harmonized bilinear network for 3d object recognition. [pytorch] [Classification.]

2019

  • [IEEE Transactions on Image Processing] 3D2SeqViews: Aggregating Sequential Views for 3D Global Feature Learning by CNN with Hierarchical Attention Aggregation . [Classification. Retrieval.]
  • [AAAI] MLVCNN: Multi-Loop-View Convolutional Neural Network for 3D Shape Retrieval. [Classification. Retrieval.]
  • [AAAI] DeepCCFV: Camera Constraint-Free Multi-View Convolutional Neural Network for 3D Object Retrieval. [Classification. Retrieval.]
  • [CVPR] Learning with Batch-wise Optimal Transport Loss for 3D Shape Recognition. [pytorch] [Classification. Retrieval.]
  • [AAAI] Angular Triplet-Center Loss for Multi-View 3D Shape Retrieval.[Classification. Retrieval.]
  • [IJCAI] Rethinking Loss Design for Large-scale 3D Shape Retrieval.[Classification. Retrieval.]
  • [IJCAI] Parts4Feature: Learning 3D Global Features from Generally Semantic Parts in Multiple Views.[Classification. Retrieval.]
  • [IJCAI] 3DViewGraph: Learning Global Features for 3D Shapes from A Graph of Unordered Views with Attention.[Classification. Retrieval.]
  • [AAAI] View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictions.[Classification. Retrieval.]
  • [ICCV] View N-gram Network for 3D Object Retrieval. [Classification. Retrieval.]

2020

  • [CVPR] View-GCN: View-based Graph Convolutional Network for 3D Shape Analysis. [pytorch][Classification. Retrieval.] πŸ”₯ ⭐

- Datasets

  • [KITTI] The KITTI Vision Benchmark Suite.
  • [ModelNet] The Princeton ModelNet .
  • [ShapeNet] A collaborative dataset between researchers at Princeton, Stanford and TTIC.
  • [PartNet] The PartNet dataset provides fine grained part annotation of objects in ShapeNetCore.
  • [PartNet] PartNet benchmark from Nanjing University and National University of Defense Technology.
  • [S3DIS] The Stanford Large-Scale 3D Indoor Spaces Dataset.
  • [ScanNet] Richly-annotated 3D Reconstructions of Indoor Scenes.
  • [Stanford 3D] The Stanford 3D Scanning Repository.
  • [Princeton Shape Benchmark] The Princeton Shape Benchmark.
  • [Large-Scale Point Cloud Classification Benchmark(ETH)] This benchmark closes the gap and provides a large labelled 3D point cloud data set of natural scenes with over 4 billion points in total.
  • [PASCAL3D+] Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild.
  • [nuScenes] The nuScenes dataset is a large-scale autonomous driving dataset.
  • [3D Match] Keypoint Matching Benchmark, Geometric Registration Benchmark, RGB-D Reconstruction Datasets.
  • [SemanticKITTI] Sequential Semantic Segmentation, 28 classes, for autonomous driving. All sequences of KITTI odometry labeled. [ICCV 2019 paper]
  • [The Waymo Open Dataset] The Waymo Open Dataset is comprised of high resolution sensor data collected by Waymo self-driving cars in a wide variety of conditions.
  • [Oxford Robotcar] The dataset captures many different combinations of weather, traffic and pedestrians.

References

Updates

  • 17/08/2020: adding view-based method and datasets

About

Deep Geometry Learning on Colab