**FFB6D** is a full flow bidirectional fusion network for 6D pose estimation of known objects from a single RGBD image. Unlike previous works that extract the RGB and point cloud features independently and fuse them in the final stage, FFB6D builds bidirectional fusion modules as communication bridges in the full flow of the two networks. In this way, the two networks can obtain complementary information from the other and learn representations containing rich appearance and geometry information of the scene.

The core ingredient of **CayleyNet** is a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest. The model generates rich spectral filters that are localized in space, scales linearly with the size of the input data for sparsely-connected graphs, and can handle different constructions of Laplacian operators.

Description adapted from: [CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters](https://arxiv.org/pdf/1705.07664.pdf)

CayleyNet

CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters

FFB6D

FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation

**HRank** is a filter pruning method that explores the High Rank of the feature map in each layer (HRank). The proposed HRank  is inspired by the discovery that the average rank of multiple feature maps generated by a single filter is always the same, regardless of the number of image batches CNNs receive. Based on HRank, the authors develop a method that is mathematically formulated to prune filters with low-rank feature maps.

Source	FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com