• Corpus ID: 198967798

DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation

@article{Zhao2019DARNetDA,
  title={DAR-Net: Dynamic Aggregation Network for Semantic Scene Segmentation},
  author={Zong-gui Zhao and Min Liu and Karthik Ramani},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.12022}
}
Traditional grid/neighbor-based static pooling has become a constraint for point cloud geometry analysis. [...] Key Method Providing variable semi-local receptive fields and weights, the skeleton serves as a bridge that connect local convolutional feature extractors and a global recurrent feature integrator. Experimental results on indoor scene datasets show advantages of the proposed approach compared to state-of-the-art architectures that adopt static pooling methods.Expand
SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation
How to learn effective features from large-scale point clouds for semantic segmentation has attracted increasing attention in recent years. Addressing this problem, we propose a learnable module that
Exploiting Structured CNNs for Semantic Segmentation of Unstructured Point Clouds from LiDAR Sensor
TLDR
This work proposes a projection-based scheme that performs an angle-wise slicing of large 3D point clouds and transforms those slices into 2D grids and employs the popular convolutional neural network (CNN) architectures to perform semantic segmentation of LiDAR data.
Are We Hungry for 3D LiDAR Data for Semantic Segmentation?
TLDR
A review of existing 3D datasets and 3D semantic segmentation methods and efforts to solve data hungry problems are summarized for both 3D LiDAR-focused methods and general-purpose methods.
Deep Learning for 3D Point Clouds: A Survey
TLDR
This paper presents a comprehensive review of recent progress in deep learning methods for point clouds, covering three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation.

References

SHOWING 1-10 OF 32 REFERENCES
3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation
TLDR
A novel end-to-end approach for unstructured point cloud semantic segmentation, named 3P-RNN, is proposed to exploit the inherent contextual features of 3D point clouds to demonstrate robust performance superior to state-of-the-arts.
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
R-Covnet: Recurrent Neural Convolution Network for 3D Object Recognition
TLDR
This paper proposes a new deep learning architecture called R-CovNet, designed for 3D object recognition, which provides a permutation invariant architecture specially designed for pointclouds data of any size.
Tangent Convolutions for Dense Prediction in 3D
TLDR
Using tangent convolutions, this work designs a deep fully-convolutional network for semantic segmentation of 3D point clouds, and applies it to challenging real-world datasets of indoor and outdoor 3D environments.
Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
TLDR
A new deep learning architecture that is designed for 3D model recognition tasks and works with unstructured point clouds, Kd-networks, which demonstrates competitive performance in a number of shape recognition tasks such as shape classification, shape retrieval and shape part segmentation.
FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-Based CNN Architecture
TLDR
This paper proposes an encoder-decoder type network, where the encoder part is composed of two branches of networks that simultaneously extract features from RGB and depth images and fuse depth features into the RGB feature maps as the network goes deeper.
Recurrent Slice Networks for 3D Segmentation of Point Clouds
TLDR
This work presents a novel 3D segmentation framework, RSNet1, to efficiently model local structures in point clouds using a combination of a novel slice pooling layer, Recurrent Neural Network layers, and a slice unpooling layer.
3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation
TLDR
3DMV is presented, a novel method for 3D semantic scene segmentation of RGB-D scans in indoor environments using a joint 3D-multi-view prediction network that achieves significantly better results than existing baselines.
SO-Net: Self-Organizing Network for Point Cloud Analysis
TLDR
The proposed SO-Net, a permutation invariant architecture for deep learning with orderless point clouds, demonstrates performance that is similar with or better than state-of-the-art approaches in recognition tasks such as point cloud reconstruction, classification, object part segmentation and shape retrieval.
SEGCloud: Semantic Segmentation of 3D Point Clouds
TLDR
SEGCloud is presented, an end-to-end framework to obtain 3D point-level segmentation that combines the advantages of NNs, trilinear interpolation(TI) and fully connected Conditional Random Fields (FC-CRF).
...
1
2
3
4
...