Paper Pool
Upcoming papers
- 01-06-2021 by Christian: Hanocka et al., MeshCNN: A Network with an Edge, 2019, ACM Trans. Graph.
- 08-06-2021 by Patrick: Wickramasinghe et al., Voxel2Mesh: 3D Mesh Model Generation from Volumetric Data, 2020, MICCAI
- 15-06-2021 by Rasmus: Paulsen et al., Multi-view consensus CNN for 3D facial landmark placement, 2018, ACCV
- 22-06-2021 by Kristine: Implicit Functions
Paper pool
Old list from the previous version of the journal club. To be updated.
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Frustum PointNets for 3D Object Detection from RGB-D Data
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling, NIPS 2016
- FPNN: Field Probing Neural Networks for 3D Data
- Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis
- DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval
- Learning shape correspondence with anisotropic convolutional neural networks
- ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
- Two Stream 3D Semantic Scene Completion
- Papers from geometric deeplearning.com, papers from this list are added to the covered list if scheduled
- Neural Scene Representation and Rendering
- Flex-Convolution (Deep Learning Beyond Grid-Worlds)
- Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
Relevant papers from CVPR 2018
- Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs
- Multi-View Harmonized Bilinear Network for 3D Object Recognition
- PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
- FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
- GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition
- Learning to Estimate 3D Human Pose and Shape From a Single Color Image
- SplineCNN: Fast Geometric Deep Learning With Continuous B-Spline Kernels
- GAGAN: Geometry-Aware Generative Adversarial Networks
- Deformable Shape Completion With Graph Convolutional Autoencoders
- Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- [Surface Networks](no link available)
- SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation
- FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
- Recurrent Slice Networks for 3D Segmentation of Point Clouds
- PU-Net: Point Cloud Upsampling Network
Papers covered
- Cao et al., A Comprehensive Survey on Geometric Deep Learning, 2020, IEEE Access (Patrick)
- SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation (Shihav)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (Vladimir)
- Cascade Multi-view Hourglass Model for Robust 3D Face Alignment (Kristine)
- Multi-view Convolutional Neural Networks for 3D Shape Recognition (Rasmus)
- Volumetric and Multi-View CNNs for Object Classification on 3D Data (Rasmus)
- Generative Adversarial Nets (Gudmundur)
- Unpaired image-to-image translation using cycle-consistent adversarial networks (Gudmundur)