Efficient Semantic Scene Completion Network with Spatial Group Convolution (2018-09-08T00:00:00.000000Z)

TL;DR

An efficient 3D sparse convolutional network is presented, which harnesses a multiscale architecture and a coarse-to-fine prediction strategy and achieves state-of-the-art performance and fast speed.

Abstract

We introduce Spatial Group Convolution (SGC) for accelerating the computation of 3D dense prediction tasks. SGC is orthogonal to group convolution, which works on spatial dimensions rather than feature channel dimension. It divides input voxels into different groups, then conducts 3D sparse convolution on these separated groups. As only valid voxels are considered when performing convolution, computation can be significantly reduced with a slight loss of accuracy. The proposed operations are validated on semantic scene completion task, which aims to predict a complete 3D volume with semantic labels from a single depth image. With SGC, we further present an efficient 3D sparse convolutional network, which harnesses a multiscale architecture and a coarse-to-fine prediction strategy. Evaluations are conducted on the SUNCG dataset, achieving state-of-the-art performance and fast speed. Code is available at this https URL

Authors

Hao Zhao

2 papers

Jiahui Zhang

4 papers

Anbang Yao

1 papers

TL;DR

Abstract

Authors

References52 items

PointCNN

3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks

3D Object Dense Reconstruction from a Single Depth View

Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in CNNs

SBNet: Sparse Blocks Network for Fast Inference

ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks

Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55

3D Graph Neural Networks for RGBD Semantic Segmentation

Scaling CNNs for High Resolution Volumetric Reconstruction from a Single Image

High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

Matterport3D: Learning from RGB-D Data in Indoor Environments

3D Object Reconstruction from a Single Depth View with Adversarial Learning

Sparsity Invariant CNNs

3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-Scale 3D Point Clouds

ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Submanifold Sparse Convolutional Networks

Learning hierarchical shape segmentation and labeling from online repositories

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models

OctNetFusion: Learning Depth Fusion from Data

Hierarchical Surface Prediction for 3D Object Reconstruction

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis

Semantic Scene Completion from a Single Depth Image

Aggregated Residual Transformations for Deep Neural Networks

OctNet: Learning Deep 3D Representations at High Resolutions

Xception: Deep Learning with Depthwise Separable Convolutions

Shape completion enabled robotic grasping

Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks

Structured Prediction of Unobserved Voxels from a Single Depth Image

FPNN: Field Probing Neural Networks for 3D Data

Volumetric and Multi-view CNNs for Object Classification on 3D Data

Identity Mappings in Deep Residual Networks

Deep Residual Learning for Image Recognition

Understanding RealWorld Indoor Scenes with Synthetic Data

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

Learning both Weights and Connections for Efficient Neural Network

U-Net: Convolutional Networks for Biomedical Image Segmentation

Sparse 3D convolutional neural networks

Predicting Complete 3D Models of Indoor Scenes

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Compressing Deep Convolutional Networks using Vector Quantization

3D ShapeNets: A deep representation for volumetric shapes

ImageNet classification with deep convolutional neural networks

Indoor Segmentation and Support Inference from RGBD Images

Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional Networks

Optimal Brain Damage

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names