Linear discrimination dictionary learning for shape descriptors

Retrieval of 3D shapes, especially non-rigid shapes, is attracting growing interest in the research community. In this paper, a new robust feature points extraction method based on two major approaches is presented. The proposed method is proven to be robust when applied to non-rigid 3D shapes as well as highly replicable in different scales. In addition, since partial features provide more detailed information regarding non-rigid 3D shape retrieval, a representation combining the global partial descriptors for 3D shape retrieval is developed and a new similarity measurement is applied to the corresponding parts of different shapes. Finally, the proposed method is implemented using global and partial descriptors with different weights. The results indicate that the proposed method efficiently performed non-rigid 3D shape retrieval.

Projective analysis is an important solution in three-dimensional (3D) shape retrieval, since human visual perceptions of 3D shapes rely on various 2D observations from different viewpoints. Although multiple informative and discriminative views are utilized, most projection-based retrieval systems suffer from heavy computational cost, and thus cannot satisfy the basic requirement of scalability for search engines. In the past three years, shape retrieval contest (SHREC) pays much attention to the scalability of 3D shape retrieval algorithms, and organizes several large scale tracks accordingly [1] – [3] . However, the experimental results indicate that conventional algorithms cannot be directly applied to large datasets. In this paper, we present a real-time 3D shape search engine based on the projective images of 3D shapes. The real-time property of our search engine results from the following aspects: 1) efficient projection and view feature extraction using GPU acceleration; 2) the first inverted file, called F-IF, is utilized to speed up the procedure of multiview matching; and 3) the second inverted file, which captures a local distribution of 3D shapes in the feature manifold, is adopted for efficient context-based reranking. As a result, for each query the retrieval task can be finished within one second despite the necessary cost of IO overhead. We name the proposed 3D shape search engine, which combines G PU acceleration and i nverted f ile ( t wice), as GIFT . Besides its high efficiency, GIFT also outperforms state-of-the-art methods significantly in retrieval accuracy on various shape benchmarks (ModelNet40 dataset, ModelNet10 dataset, PSB dataset, McGill dataset) and competitions (SHREC14LSGTB, ShapeNet Core55, WM-SHREC07).

A spectral graph wavelet approach for nonrigid 3D shape retrieval

Recently, feature-learning-based 3D shape retrieval methods have been receiving more and more attention in the 3D shape analysis community. In these methods, the hand-crafted metrics or the learned linear metrics are usually used to compute the distances between shape features. Since there are complex geometric structural variations with 3D shapes, the single hand-crafted metric or learned linear metric cannot characterize the manifold, where 3D shapes lie well. In this paper, by exploring the nonlinearity of the deep neural network and the complementarity among multiple shape features, we propose a novel deep multimetric network for 3D shape retrieval. The developed multimetric network minimizes a discriminative loss function that, for each type of shape feature, the outputs of the network from the same class are encouraged to be as similar as possible and the outputs from different classes are encouraged to be as dissimilar as possible. Meanwhile, the Hilbert-Schmidt independence criterion is employed to enforce the outputs of different types of shape features to be as complementary as possible. Furthermore, the weights of the learned multiple distance metrics can be adaptively determined in our developed deep metric network. The weighted distance metric is then used as the similarity for shape retrieval. We conduct experiments with the proposed method on the four benchmark shape datasets. Experimental results demonstrate that the proposed method can obtain better performance than the learned deep single metric and outperform the state-of-the-art 3D shape retrieval methods.

3D shape retrieval has attracted much research attention due to its wide applications in the fields of computer vision and multimedia. Various approaches have been proposed in recent years for learning 3D shape descriptor from different modalities. The existing works contain the following disadvantages: 1) the vast majority methods rely on the large scale of training data with clear category information; 2) many approaches focus on the fusion of multi-modal information but ignore the guidance of correlations among different modalities for shape representation learning; 3) many methods pay attention to the structural feature learning of 3D shape but ignore the guidance of structural similarity between every two shapes. To solve these problems, we propose a novel multi-graph network (MGN) for unsupervised 3D shape retrieval, which utilizes the correlations among modalities and structural similarity between two models to guide the shape representation learning process without category information. More specifically, we propose two novel loss functions: auto-correlation loss and cross-correlation loss. The auto-correlation loss utilizes information from different modalities to increase the discrimination of shape descriptor. The cross-correlation loss utilizes the structural similarity between two models to strengthen the intra-class similarity and increase the inter-class distinction. Finally, an effective similarity measurement is designed for the shape retrieval task. To validate the effectiveness of our proposed method, we conduct experiments on the ModelNet dataset. Experimental results demonstrate the effectiveness of our proposed method, and significant improvements have been achieved compared with state-of-the-art methods.

Highly discriminative 3D shape representations can be formed by encoding the spatial relationship among virtual words into the Bag of Words (BoW) method. To achieve this challenging task, several unresolved issues in the encoding procedure must be overcome for 3D shapes, including: 1) arbitrary mesh resolution; 2) irregular vertex topology; 3) orientation ambiguity on the 3D surface; and 4) invariance to rigid and non-rigid shape transformations. In this paper, a novel spatially enhanced 3D shape representation called bag of spatial context correlations (BoSCCs) is proposed to address all these issues. Adopting a novel local perspective, BoSCC is able to describe a 3D shape by an occurrence frequency histogram of spatial context correlation patterns, which makes BoSCC become more compact and discriminative than previous global perspective-based methods. Specifically, the spatial context correlation is proposed to simultaneously encode the geometric and spatial information of a 3D local region by the correlation among spatial contexts of vertices in that region, which effectively resolves the aforementioned issues. The spatial context of each vertex is modeled by Markov chains in a multi-scale manner, which thoroughly captures the spatial relationship by the transition probabilities of intra-virtual words and the ones of inter-virtual words. The high discriminability and compactness of BoSCC are effective for classification and retrieval, especially in the scenarios of limited samples and partial shape retrieval. Experimental results show that BoSCC outperforms the state-of-the-art spatially enhanced BoW methods in three common applications: global shape retrieval, shape classification, and partial shape retrieval.

RJAN: Region‐based joint attention network for 3D shape recognition

Over the past few years, Generative Adversarial Networks (GANs) have garnered increased interest among researchers in Computer Vision, with applications including, but not limited to, image generation, translation, imputation, and super-resolution. Nevertheless, no GAN-based method has been proposed in the literature that can successfully represent, generate or translate 3D facial shapes (meshes). This can be primarily attributed to two facts, namely that (a) publicly available 3D face databases are scarce as well as limited in terms of sample size and variability (e.g., few subjects, little diversity in race and gender), and (b) mesh convolutions for deep networks present several challenges that are not entirely tackled in the literature, leading to operator approximations and model instability, often failing to preserve high-frequency components of the distribution. As a result, linear methods such as Principal Component Analysis (PCA) have been mainly utilized towards 3D shape analysis, despite being unable to capture non-linearities and high frequency details of the 3D face—such as eyelid and lip variations. In this work, we present 3DFaceGAN, the first GAN tailored towards modeling the distribution of 3D facial surfaces, while retaining the high frequency details of 3D face shapes. We conduct an extensive series of both qualitative and quantitative experiments, where the merits of 3DFaceGAN are clearly demonstrated against other, state-of-the-art methods in tasks such as 3D shape representation, generation, and translation.

With the advent of commodity 3D capturing devices and better 3D modeling tools, 3D shape content is becoming increasingly prevalent. Therefore, the need for shape retrieval algorithms to handle large-scale shape repositories is more and more important. This track provides a benchmark to evaluate large-scale 3D shape retrieval based on the ShapeNet dataset. It is a continuation of the SHREC 2016 large-scale shape retrieval challenge with a goal of measuring progress with recent developments in deep learning methods for shape retrieval. We use ShapeNet Core55, which provides more than 50 thousands models over 55 common categories in total for training and evaluating several algorithms. Eight participating teams have submitted a variety of retrieval methods which were evaluated on several standard information retrieval performance metrics. The approaches vary in terms of the 3D representation, using multi-view projections, point sets, volumetric grids, or traditional 3D shape descriptors. Overall performance on the shape retrieval task has improved significantly compared to the iteration of this competition in SHREC 2016. We release all data, results, and evaluation code for the benefit of the community and to catalyze future research into large-scale 3D shape retrieval (website: https://www.shapenet.org/shrec17).

The recent advances of low-cost and mobile depth sensors dramatically extend the potential of 3D shape retrieval and analysis. While the traditional research of 3D retrieval mainly focused on searching by a rough 2D sketch or with a high-quality CAD model, we tackle a novel and challenging problem of cross-domain 3D shape retrieval, in which users can use 3D scans from low-cost depth sensors like Kinect as queries to search CAD models in the database. To cope with the imperfection of user-captured models such as model noise and occlusion, we propose a cross-domain shape retrieval framework, which minimizes the potential function of a Conditional Random Field to efficiently generate the retrieval scores. In particular, the potential function consists of two critical components: one unary potential term provides robust cross-domain partial matching and the other pairwise potential term embeds spatial structures to alleviate the instability from model noise. Both potential components are efficiently estimated using random forests with 3D local features, forming a Regression Tree Field framework. We conduct extensive experiments on two recently released user-captured 3D shape datasets and compare with several state-of-the-art approaches on the cross-domain shape retrieval task. The experimental results demonstrate that our proposed method outperforms the competing methods with a significant performance gain.

We present O-CNN , an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, our method takes the average normal vectors of a 3D model sampled in the finest leaf octants as input and performs 3D CNN operations on the octants occupied by the 3D shape surface. We design a novel octree data structure to efficiently store the octant information and CNN features into the graphics memory and execute the entire O-CNN training and evaluation on the GPU. O-CNN supports various CNN structures and works for 3D shapes in different representations. By restraining the computations on the octants occupied by 3D surfaces, the memory and computational costs of the O-CNN grow quadratically as the depth of the octree increases, which makes the 3D CNN feasible for high-resolution 3D models. We compare the performance of the O-CNN with other existing 3D CNN solutions and demonstrate the efficiency and efficacy of O-CNN in three shape analysis tasks, including object classification, shape retrieval, and shape segmentation.

In perceiving 3D shape from ambiguous shading patterns, humans use the prior knowledge that the light is located above their head and slightly to the left. Although this observation has fascinated scientists and artists for a long time, the neural basis of this "light from above left" preference for the interpretation of 3D shape remains largely unexplored. Combining behavioral and functional MRI measurements coupled with multivoxel pattern analysis, we show that activations in early visual areas predict best the light source direction irrespective of the perceived shape, but activations in higher occipitotemporal and parietal areas predict better the perceived 3D shape irrespective of the light direction. These findings demonstrate that illumination is processed earlier than the representation of 3D shape in the visual system. In contrast to previous suggestions, we propose that prior knowledge about illumination is processed in a bottom-up manner and influences the interpretation of 3D structure at higher stages of processing.

Recently, content based 3D shape retrieval has been an active area of research. Benchmarking allows researchers to evaluate the quality of results of different 3D shape retrieval approaches. Here, we propose a new publicly available 3D shape benchmark to advance the state of art in 3D shape retrieval. We provide a review of previous and recent benchmarking efforts and then discuss some of the issues and problems involved in developing a benchmark. A detailed description of the new shape benchmark is provided including some of the salient features of this benchmark. In this benchmark, the 3D models are classified mainly according to visual shape similarity but in contrast to other benchmarks, the geometric structure of each model is modified and normalized, with each class in the benchmark sharing the equal number of models to reduce the possible bias in evaluation results. In the end we evaluate several representative algorithms for 3D shape searching on the new benchmark, and a comparison experiment between different shape benchmarks is also conducted to show the reliability of the new benchmark.

3D shape determines an object's physical properties to a large degree. In this article, we introduce an autonomous learning system for categorizing 3D shape of simulated objects from single views. The system extends an unsupervised bottom-up learning architecture based on the slowness principle with top-down information derived from the physical behavior of objects. The unsupervised bottom-up learning leads to pose invariant representations. Shape specificity is then integrated as top-down information from the movement trajectories of the objects. As a result, the system can categorize 3D object shape from a single static object view without supervised postprocessing.

Content-based 3D shape retrieval is an important problem in computer vision. Traditional retrieval interfaces require a 2D sketch or a manually designed 3D model as the query, which is difficult to specify and thus not practical in real applications. With the recent advance in low-cost 3D sensors such as Microsoft Kinect and Intel Realsense, capturing depth images that carry 3D information is fairly simple, making shape retrieval more practical and user-friendly. In this paper, we study the problem of cross-domain 3D shape retrieval using a single depth image from low-cost sensors as the query to search for similar human designed CAD models. We propose a novel method using an ensemble of autoencoders in which each autoencoder is trained to learn a compressed representation of depth views synthesize d from each database object. By viewing each autoencoder as a probabilistic model, a likelihood score can be derived as a similarity measure. A domain adaptation layer is built on top of autoencoder outputs to explicitly address the cross-domain issue (between noisy sensory data and clean 3D models) by incorporating training data of sensor depth images and their category labels in a weakly supennsed learning formulation. Experiments using real-world depth images and a large-scale CAD dataset demonstrate the effectiveness of our approach, which offers significant improvements over state-of-the-art 3D shape retrieval methods.