• Corpus ID: 222125136

RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval

  title={RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval},
  author={Rao Fu and Jie Yang and Jiawei Sun and Fang-Lue Zhang and Yu-Kun Lai and Lin Gao},
Fine-grained 3D shape retrieval aims to retrieve 3D shapes similar to a query shape in a repository with models belonging to the same class, which requires shape descriptors to be capable of representing detailed geometric information to discriminate shapes with globally similar structures. Moreover, 3D objects can be placed with arbitrary position and orientation in real-world applications, which further requires shape descriptors to be robust to rigid transformations. The shape descriptions… 

Using Learned Visual and Geometric Features to Retrieve Complete 3D Proxies for Broken Objects

The approach outperforms the existing state-of-the-art method in retrieval of proxies for broken objects in terms of the Chamfer distance and enables understanding of object geometry to identify object portions requiring repair, to incorporate user preferences, and to generate 3D printable restoration components.

A Revisit of Shape Editing Techniques: From the Geometric to the Neural Viewpoint

Recent research studies from the geometric viewpoint to those emerging neural deformation techniques are surveyed and categorize them into organic shape editing methods and man-made model editing methods.



Learning the Compositional Structure of Man-Made Objects for 3D Shape Retrieval

A feature selection technique that decomposes 3D point clouds into sections that can be represented by a plane, a sphere, a cylinder, a cone, or a torus is proposed and a probabilistic framework for analyzing and learning the spatial arrangement of the detected shape primitives with respect to training objects belonging to certain categories is introduced.

GIFT: A Real-Time and Scalable 3D Shape Search Engine

The proposed 3D shape search engine, which combines GPU acceleration and Inverted File (Twice), is named as GIFT, which outperforms the state-of-the-art methods significantly in retrieval accuracy on various shape benchmarks and competitions.

Deep Aggregation of Local 3D Geometric Features for 3D Model Retrieval

A novel deep neural network called Deep Local feature Aggregation Network (DLAN) is proposed that combines extraction of rotation-invariant 3D local features and their aggregation in a single deep architecture and Experimental evaluation shows that the DLAN outperforms the existing deep learning-based 3DMR algorithms.

Deformation-Aware 3D Model Embedding and Retrieval

This work introduces a new problem of retrieving 3D models that are deformable to a given query shape and presents a novel deep deformation-aware embedding to solve this retrieval task and proposes two strategies for training the embedding network.

Multi-view Convolutional Neural Networks for 3D Shape Recognition

This work presents a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and shows that a 3D shape can be recognized even from a single view at an accuracy far higher than using state-of-the-art3D shape descriptors.

ShapeNet: An Information-Rich 3D Model Repository

ShapeNet contains 3D models from a multitude of semantic categories and organizes them under the WordNet taxonomy, a collection of datasets providing many semantic annotations for each 3D model such as consistent rigid alignments, parts and bilateral symmetry planes, physical sizes, keywords, as well as other planned annotations.

Shape google: Geometric words and expressions for invariant shape retrieval

This article uses multiscale diffusion heat kernels as “geometric words” to construct compact and informative shape descriptors by means of the “bag of features” approach, and shows that shapes can be efficiently represented as binary codes.

SURFing the point clouds: Selective 3D spatial pyramids for category-level object recognition

A Bag-of-Words representation in 3D, which is used in conjunction with a SVM classification machinery, and the 3D Spatial Pyramid Matching Kernel, which works by partitioning a working volume into fine sub-volumes, and computing a hierarchical weighted sum of histogram intersections at each level of the pyramid structure.

Learned Binary Spectral Shape Descriptor for 3D Shape Correspondence

  • J. XieM. WangYi Fang
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
A novel binary spectral shape descriptor is proposed with the deep neural network for 3D shape correspondence that can require less storage space and enable fast matching.

Deep Learning 3D Shape Surfaces Using Geometry Images

This work qualitatively and quantitatively validate that creating geometry images using authalic parametrization on a spherical domain is suitable for robust learning of 3D shape surfaces, and proposes a way to implicitly learn the topology and structure of3D shapes using geometry images encoded with suitable features.