3D Convolution
Description
A 3D Convolution is a type of convolution where the kernel slides in 3 dimensions as opposed to 2 dimensions with 2D convolutions. One example use case is medical imaging where a model is constructed using 3D image slices. Additionally video based data has an additional temporal dimension over images making it suitable for this module.
Image: Lung nodule detection based on 3D convolutional neural networks, Fan et al
Papers Using This Method
Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control2025-05-22HandReader: Advanced Techniques for Efficient Fingerspelling Recognition2025-05-15UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection2025-03-15BILLNET: A Binarized Conv3D-LSTM Network with Logic-gated residual architecture for hardware-efficient video inference2025-01-24Swin-X2S: Reconstructing 3D Shape from 2D Biplanar X-ray with Swin Transformers2025-01-10SuperLightNet: Lightweight Parameter Aggregation Network for Multimodal Brain Tumor Segmentation2025-01-01ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection2024-12-11Lightweight Spatial Embedding for Vision-based 3D Occupancy Prediction2024-12-08Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT Segmentation2024-11-20Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation2024-11-03Cross-D Conv: Cross-Dimensional Transferable Knowledge Base via Fourier Shifting Operation2024-11-02Preserving Cardiac Integrity: A Topology-Infused Approach to Whole Heart Segmentation2024-10-14Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction2024-10-08Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement2024-07-18Bidirectional Stereo Image Compression with Cross-Dimensional Entropy Model2024-07-153D Adaptive Structural Convolution Network for Domain-Invariant Point Cloud Recognition2024-07-05Towards Automating the Retrospective Generation of BIM Models: A Unified Framework for 3D Semantic Reconstruction of the Built Environment2024-06-03ARCH2S: Dataset, Benchmark and Challenges for Learning Exterior Architectural Structures from Point Clouds2024-06-03Ghost-Stereo: GhostNet-based Cost Volume Enhancement and Aggregation for Stereo Matching Networks2024-05-23LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels2024-03-22