skip to main content

Title: Directionally Convolutional Networks for 3D Shape Segmentation
Previous approaches on 3D shape segmentation mostly rely on heuristic processing and hand-tuned geometric descriptors. In this paper, we propose a novel 3D shape representation learning approach, Directionally Convolutional Network (DCN), to solve the shape segmentation problem. DCN extends convolution operations from images to the surface mesh of 3D shapes. With DCN, we learn effective shape representations from raw geometric features, i.e., face normals and distances, to achieve robust segmentation. More specifically, a two-stream segmentation framework is proposed: one stream is made up by the proposed DCN with the face normals as the input, and the other stream is implemented by a neural network with the face distance histogram as the input. The learned shape representations from the two streams are fused by an element-wise product. Finally, Conditional Random Field (CRF) is applied to optimize the segmentation. Through extensive experiments conducted on benchmark datasets, we demonstrate that our approach outperforms the current state-of-the-arts (both classic and deep learning-based) on a large variety of 3D shapes.
; ;
Award ID(s):
Publication Date:
Journal Name:
IEEE International Conference on Computer Vision (ICCV)
Page Range or eLocation-ID:
2698 - 2707
Sponsoring Org:
National Science Foundation
More Like this
  1. Learning pose invariant representation is a fundamental problem in shape analysis. Most existing deep learning algorithms for 3D shape analysis are not robust to rotations and are often trained on synthetic datasets consisting of pre-aligned shapes, yielding poor generalization to unseen poses. This observation motivates a growing interest in rotation invariant and equivariant methods. The field of rotation equivariant deep learning is developing in recent years thanks to a well established theory of Lie group representations and convolutions. A fundamental problem in equivariant deep learning is to design activation functions which are both informative and preserve equivariance. The recently introduced Tensor Field Network (TFN) framework provides a rotation equivariant network design for point cloud analysis. TFN features undergo a rotation in feature space given a rotation of the input pointcloud. TFN and similar designs consider nonlinearities which operate only over rotation invariant features such as the norm of equivariant features to preserve equivariance, making them unable to capture the directional information. In a recent work entitled "Gauge Equivariant Mesh CNNs: Anisotropic Convolutions on Geometric Graphs" Hann et al. interpret 2D rotation equivariant features as Fourier coefficients of functions on the circle. In this work we transpose the idea of Hannmore »et al. to 3D by interpreting TFN features as spherical harmonics coefficients of functions on the sphere. We introduce a new equivariant nonlinearity and pooling for TFN. We show improvments over the original TFN design and other equivariant nonlinearities in classification and segmentation tasks. Furthermore our method is competitive with state of the art rotation invariant methods in some instances.« less
  2. This paper introduces a deep neural network based method, i.e., DeepOrganNet, to generate and visualize fully high-fidelity 3D / 4D organ geometric models from single-view medical images with complicated background in real time. Traditional 3D / 4D medical image reconstruction requires near hundreds of projections, which cost insufferable computational time and deliver undesirable high imaging / radiation dose to human subjects. Moreover, it always needs further notorious processes to segment or extract the accurate 3D organ models subsequently. The computational time and imaging dose can be reduced by decreasing the number of projections, but the reconstructed image quality is degraded accordingly. To our knowledge, there is no method directly and explicitly reconstructing multiple 3D organ meshes from a single 2D medical grayscale image on the fly. Given single-view 2D medical images, e.g., 3D / 4D-CT projections or X-ray images, our end-to-end DeepOrganNet framework can efficiently and effectively reconstruct 3D / 4D lung models with a variety of geometric shapes by learning the smooth deformation fields from multiple templates based on a trivariate tensor-product deformation technique, leveraging an informative latent descriptor extracted from input 2D images. The proposed method can guarantee to generate high-quality and high-fidelity manifold meshes for 3D /more »4D lung models; while, all current deep learning based approaches on the shape reconstruction from a single image cannot. The major contributions of this work are to accurately reconstruct the 3D organ shapes from 2D single-view projection, significantly improve the procedure time to allow on-the-fly visualization, and dramatically reduce the imaging dose for human subjects. Experimental results are evaluated and compared with the traditional reconstruction method and the state-of-the-art in deep learning, by using extensive 3D and 4D examples, including both synthetic phantom and real patient datasets. The efficiency of the proposed method shows that it only needs several milliseconds to generate organ meshes with 10K vertices, which has great potential to be used in real-time image guided radiation therapy (IGRT).« less
  3. Many industries, such as human-centric product manufacturing, are calling for mass customization with personalized products. One key enabler of mass customization is 3D printing, which makes flexible design and manufacturing possible. However, the personalized designs bring challenges for the shape matching and analysis, owing to the high complexity and shape variations. Traditional shape matching methods are limited to spatial alignment and finding a transformation matrix for two shapes, which cannot determine a vertex-to-vertex or feature-to-feature correlation between the two shapes. Hence, such a method cannot measure the deformation of the shape and interested features directly. To measure the deformations widely seen in the mass customization paradigm and address the issues of alignment methods in shape matching, we identify the geometry matching of deformed shapes as a correspondence problem. The problem is challenging due to the huge solution space and nonlinear complexity, which is difficult for conventional optimization methods to solve. According to the observation that the well-established massive databases provide the correspondence results of the treated teeth models, a learning-based method is proposed for the shape correspondence problem. Specifically, a state-of-the-art geometric deep learning method is used to learn the correspondence of a set of collected deformed shapes. Through learningmore »the deformations of the models, the underlying variations of the shapes are extracted and used for finding the vertex-to-vertex mapping among these shapes. We demonstrate the application of the proposed approach in the orthodontics industry, and the experimental results show that the proposed method can predict correspondence fast and accurate, also robust to extreme cases. Furthermore, the proposed method is favorably suitable for deformed shape analysis in mass customization enabled by 3D printing.« less
  4. The success of supervised learning requires large-scale ground truth labels which are very expensive, time- consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are developed. Unlike most existing self-supervised methods to learn only 2D image features or only 3D point cloud features, this paper presents a novel and effective self-supervised learning approach to jointly learn both 2D image features and 3D point cloud features by exploiting cross-modality and cross-view correspondences without using any human annotated labels. Specifically, 2D image features of rendered images from different views are extracted by a 2D convolutional neural network, and 3D point cloud features are extracted by a graph convolution neural network. Two types of features are fed into a two-layer fully connected neural network to estimate the cross-modality correspondence. The three networks are jointly trained (i.e. cross-modality) by verifying whether two sampled data of different modalities belong to the same object, meanwhile, the 2D convolutional neural network is additionally optimized through minimizing intra-object distance while maximizing inter-object distance of rendered images in different views (i.e. cross-view). The effectiveness of the learned 2D and 3D features is evaluated by transferring them on five different tasks includingmore »multi-view 2D shape recognition, 3D shape recognition, multi-view 2D shape retrieval, 3D shape retrieval, and 3D part-segmentation. Extensive evaluations on all the five different tasks across different datasets demonstrate strong generalization and effectiveness of the learned 2D and 3D features by the proposed self-supervised method.« less
  5. We investigate the role of representations and architectures for classifying 3D shapes in terms of their computational efficiency, generalization, and robustness to adversarial transformations. By varying the number of training examples and employing cross-modal transfer learning we study the role of initialization of existing deep architectures for 3D shape classification. Our analysis shows that multiview methods continue to offer the best generalization even without pretraining on large labeled image datasets, and even when trained on simplified inputs such as binary silhouettes. Furthermore, the performance of voxel-based 3D convolutional networks and point-based architectures can be improved via cross-modal transfer from image representations. Finally, we analyze the robustness of 3D shape classifiers to adversarial transformations and present a novel approach for generating adversarial perturbations of a 3D shape for multiview classifiers using a differentiable renderer. We find that point-based networks are more robust to point position perturbations while voxel-based and multiview networks are easily fooled with the addition of imperceptible noise to the input.