Tabulated MLP for Fast Point Feature Embedding
Explore this paper's citation graph
Summary
A new framework that uses a pair of multi-layer perceptron (MLP) and look-up table (LUT) to transform point-coordinate inputs into high-dimensional features and yields performance comparable to that of MLP while achieving significant speedup.
- Type
- preprint
- Published
- 2019-11-23
- Cited by
- 6
- References
- 29
- Access
- Open access
- OpenAlex
- https://openalex.org/W2990565762
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:208527241
Keywords
Speedup, Embedding, Jacobian matrix and determinant, Computer science, Lookup table
References
- Learning representations by back-propagating errors
- Learning Spatiotemporal Features with 3D Convolutional Networks
- Fast High‐Dimensional Filtering Using the Permutohedral Lattice
- A 128× 128 120 dB 15 Latency Asynchronous Temporal Contrast Vision Sensor
- Lucas-Kanade 20 Years On: A Unifying Framework
- ShapeNet: An Information-Rich 3D Model Repository
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
- Frustum PointNets for 3D Object Detection from RGB-D Data
- Large-Scale Point Cloud Semantic Segmentation with Superpoint Graphs
- VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection
- SPLATNet: Sparse Lattice Networks for Point Cloud Processing
- Classification of Point Cloud Scenes with Multiscale Voxel Deep Network
- Automatic differentiation in PyTorch
- EventNet: Asynchronous Recursive Event Processing
- PointPillars: Fast Encoders for Object Detection From Point Clouds
- KPConv: Flexible and Deformable Convolution for Point Clouds
- Deep Closest Point: Learning Representations for Point Cloud Registration
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Cited by
- Deep Global Features for Point Cloud Alignment
- Rethinking PointNet Embedding for Faster and Compact Model
- An Efficient Accelerator for Deep Learning-based Point Cloud Registration on FPGAs
- Federated Learning for Large-Scale Scene Modeling with Neural Radiance Fields
- FPGA-accelerated Correspondence-free Point Cloud Registration with PointNet Features
- 3D Gaussian Point Encoders
Related papers
- Comparison of sinusoidal perceptron with multilayer classical perceptron
- Single-layer perception capable of classifying 2N+1 distinct input patterns
- Prediction of significant wave height using geno-multilayer perceptron
- Performance Comparison of Multi-layer Perceptron (Back Propagation, Delta Rule and Perceptron) algorithms in Neural Networks
- Kajian Literatur Multi Layer Perceptron Seberapa Baik Performa Algoritma Ini
- Multiple threshold perceptron using sinusoidal function
- Global Convergence and Limit Cycle Behavior of Weights of Perceptron