3D Shape Segmentation with Projective Convolutional Networks

2016-12-08 · CVPR 2017 7 · Evangelos Kalogerakis, Melinos Averkiou, Subhransu Maji, Siddhartha Chaudhuri

This paper introduces a deep architecture for segmenting 3D objects into their labeled semantic parts. Our architecture combines image-based Fully Convolutional Networks (FCNs) and surface-based Conditional Random Fields (CRFs) to yield coherent segmentations of 3D shapes. The image-based FCNs are used for efficient view-based reasoning about 3D object parts. Through a special projection layer, FCN outputs are effectively aggregated across multiple views and scales, then are projected onto the 3D object surfaces. Finally, a surface-based CRF combines the projected outputs with geometric consistency cues to yield coherent segmentations. The whole architecture (multi-view FCNs and CRF) is trained end-to-end. Our approach significantly outperforms the existing state-of-the-art methods in the currently largest segmentation benchmark (ShapeNet). Finally, we demonstrate promising segmentation results on noisy 3D shapes acquired from consumer-grade depth cameras.

📄 PDF Abstract BibTeX arXiv:1612.02808

Code (1)

kalov/ShapePFCN

Tasks

Segmentation

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

CRF Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is…

FCN Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as…

Manifolds of Projective Shapes

2016-02-13 · Thomas Hotz, Florian Kelma, John T. Kent

The projective shape of a configuration of k points or "landmarks" in RP(d) consists of the information that is invariant under projective transformations and hence is reconstructable from uncalibrated camera views. Math…

Shape-Preserving Half-Projective Warps for Image Stitching

2014-06-01 · CVPR 2014 6 · Che-Han Chang, Yoichi Sato, Yung-Yu Chuang

This paper proposes a novel parametric warp which is a spatial combination of a projective transformation and a similarity transformation. Given the projective transformation relating two input images, based on an analys…

Image Stitching

Projective Skip-Connections for Segmentation Along a Subset of Dimensions in Retinal OCT

2021-08-02 · Dmitrii Lachinov, Philipp Seeboeck, Julia Mai, Ursula Schmidt-Erfurth 외

In medical imaging, there are clinically relevant segmentation tasks where the output mask is a projection to a subset of input image dimensions. In this work, we propose a novel convolutional neural network architecture…

Decoder image-classification Image Classification Image Segmentation+2

What are the Receptive, Effective Receptive, and Projective Fields of Neurons in Convolutional Neural Networks?

2017-05-19 · Hung Le, Ali Borji

In this work, we explain in detail how receptive fields, effective receptive fields, and projective fields of neurons in different layers, convolution or pooling, of a Convolutional Neural Network (CNN) are calculated. W…

3D Shape Segmentation via Shape Fully Convolutional Networks

2017-02-28 · Pengyu Wang, Yuan Gan, Panpan Shui, Fenggen Yu 외

We desgin a novel fully convolutional network architecture for shapes, denoted by Shape Fully Convolutional Networks (SFCN). 3D shapes are represented as graph structures in the SFCN architecture, based on novel graph co…

Image Segmentation Segmentation Semantic Segmentation