Shape recognition is the main challenging problem in computer vision. Different approaches and tools are used to solve this problem. Most existing approaches to object recognition are based on pixels. Pixel-based methods are dependent on the geometry and nature of the pixels, so the destruction of pixels reduces their performance. In this paper, we study the ability of graphs as shape recognition. We construct a graph that captures the topological and geometrical properties of the object. Then, using the coordinate and relation of its vertices, we extract features that are robust to noise, rotation, scale variation, and articulation. To evaluate our method, we provide different comparisons with state-of-the-art results on various known benchmarks, including Kimia's, Tari56, Tetrapod, and Articulated dataset. We provide an analysis of our method against different variations. The results confirm our performance, especially against noise.
Shanghai University（上海大学）；Huazhong University of Science and Technology（华中科技大学）
Contour and skeleton are two complementary representations for shape recognition. However combining them in a principal way is nontrivial, as they are generally abstracted by different structures (closed string vs graph), respectively. This paper aims at addressing the shape recognition problem by combining contour and skeleton according to the correspondence between them. The correspondence provides a straightforward way to associate skeletal information with a shape contour. More specifically, we propose a new shape descriptor. named Skeleton-associated Shape Context (SSC), which captures th…
School of Electronics Engineering, VIT University（VIT大学电子工程学院）
Computer vision helps machines or computer to see like humans. Computer Takes information from the images and then understands of useful information from images. Gesture recognition and movement recognition are the current area of research in computer vision. For both gesture and movement recognition finding pose of an object is of great importance. The purpose of this paper is to review many state of art which is already available for finding the pose of object based on shape, based on appearance, based on feature and comparison for its accuracy, complexity and performance
3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on point-cloud data or multi-view data alone. However, in the era of big data, integrating data of two different modals to obtain a unified 3D shape descriptor is bound to improve the recognition accuracy. Therefore, this paper proposes a fusion network based on multimodal attention mechanism for 3D shape recognition. Considering the limitations of multi-view data, …
Sichuan University（四川大学）；Michigan State University（密歇根州立大学）
This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously. Unlike existing 3D face reconstruction methods, our proposed method directly regresses dense 3D face shapes from single 2D images, and tackles identity and residual (i.e., non-identity) components in 3D face shapes explicitly and separately based on a composite 3D face shape model with latent representation…
Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
We present a new deep learning architecture (called Kd-network) that is designed for 3D model recognition tasks and works with unstructured point clouds. The new architecture performs multiplicative transformations and share parameters of these transformations according to the subdivisions of the point clouds imposed onto them by Kd-trees. Unlike the currently dominant convolutional architectures that usually require rasterization on uniform two-dimensional or three-dimensional grids, Kd-networks do not rely on such grids in any way and therefore avoid poor scaling behaviour. In a series of ex…
View-based approach that recognizes 3D shape through its projected 2D images achieved state-of-the-art performance for 3D shape recognition. One essential challenge for view-based approach is how to aggregate the multi-view features extracted from 2D images to be a global 3D shape descriptor. In this work, we propose a novel feature aggregation network by fully investigating the relations among views. We construct a relational graph with multi-view images as nodes, and design relational graph embedding by modeling pairwise and neighboring relations among views. By gradually coarsening the grap…
We demonstrate that a generative model for object shapes can achieve state of the art results on challenging scene text recognition tasks, and with orders of magnitude fewer training images than required for competing discriminative methods. In addition to transcribing text from challenging images, our method performs fine-grained instance segmentation of characters. We show that our model is more robust to both affine transformations and non-affine deformations compared to previous approaches.
The paper investigates a hypothesis that our visual system groups visual cues based on how they form a surface, or more specifically triangulation derived from the visual cues. To test our hypothesis, we compare shape recognition with three different representations of visual cues: a set of isolated dots delineating the outline of the shape, a set of triangles obtained from Delaunay triangulation of the set of dots, and a subset of Delaunay triangles excluding those outside of the shape. Each participant was assigned to one particular representation type and increased the number of dots (and c…
Because the magnitude of inner products with its basis functions are invariant to rotation and scale change, the Fourier-Mellin transform has long been used as a component in Euclidean invariant 2D shape recognition systems. Yet Fourier-Mellin transform magnitudes are only invariant to rotation and scale changes about a known center point, and full Euclidean invariant shape recognition is not possible except when this center point can be consistently and accurately identified. In this paper, we describe a system where a Fourier-Mellin transform is computed at every point in the image. The spat…
Islamia College Peshawar (Chartered University)（白沙瓦伊斯兰学院（特许大学））；National University of Computer and Emerging Sciences（国立计算机与新兴科学大学）
Retrieving similar images from a large dataset based on the image content has been a very active research area and is a very challenging task. Studies have shown that retrieving similar images based on their shape is a very effective method. For this purpose a large number of methods exist in literature. The combination of more than one feature has also been investigated for this purpose and has shown promising results. In this paper a fusion based shapes recognition method has been proposed. A set of local boundary based and region based features are derived from the labeled grid based repres…
City University of Hong Kong（香港城市大学）；COMSATS University Islamabad（COMSATS大学伊斯兰堡校区）
Dynamic facial expression recognition has many useful applications in social networks, multimedia content analysis, security systems and others. This challenging process must be done under recurrent problems of image illumination and low resolution which changes at partial occlusions. This paper aims to produce a new facial expression recognition method based on the changes in the facial muscles. The geometric features are used to specify the facial regions i.e., mouth, eyes, and nose. The generic Fourier shape descriptor in conjunction with elliptic Fourier shape descriptor is used as an attr…
Chongqing University（重庆大学）；Beihang University（北京航空航天大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
We further exploit the representational power of Haar wavelet and present a novel low-level face representation named Shape Primitives Histogram (SPH) for face recognition. Since human faces exist abundant shape features, we address the face representation issue from the perspective of the shape feature extraction. In our approach, we divide faces into a number of tiny shape fragments and reduce these shape fragments to several uniform atomic shape patterns called Shape Primitives. A convolution with Haar Wavelet templates is applied to each shape fragment to identify its belonging shape primi…
3D object recognition has attracted wide research attention in the field of multimedia and computer vision. With the recent proliferation of deep learning, various deep models with different representations have achieved the state-of-the-art performance. Among them, point cloud and multi-view based 3D shape representations are promising recently, and their corresponding deep models have shown significant performance on 3D shape recognition. However, there is little effort concentrating point cloud data and multi-view data for 3D shape representation, which is, in our consideration, beneficial …
Institute of Advanced Artificial Intelligence in Nanjing（南京先进人工智能研究所）；Horizon Robotics（地平线机器人（Horizon Robotics））
Deep metric learning is essential for visual recognition. The widely used pair-wise (or triplet) based loss objectives cannot make full use of semantical information in training samples or give enough attention to those hard samples during optimization. Thus, they often suffer from a slow convergence rate and inferior performance. In this paper, we show how to learn an importance-driven distance metric via optimal transport programming from batches of samples. It can automatically emphasize hard examples and lead to significant improvements in convergence. We propose a new batch-wise optimal t…
The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
In 3D shape recognition, multi-view based methods leverage human's perspective to analyze 3D shapes and have achieved significant outcomes. Most existing research works in deep learning adopt handcrafted networks as backbones due to their high capacity of feature extraction, and also benefit from ImageNet pretraining. However, whether these network architectures are suitable for 3D analysis or not remains unclear. In this paper, we propose a neural architecture search method named Auto-MVCNN which is particularly designed for optimizing architecture in multi-view 3D shape recognition. Auto-MVC…
Nimra Institute of Science & Technology（尼姆拉理工学院）；JNTUH（贾瓦哈拉尔·尼赫鲁科技大学）
Object recognition is still an impediment in the field of computer vision and multimedia retrieval.Defining an object model is a critical task. Shape information of an object play a critical role in the process of object recognition. Extraction of boundary information of an object from the multimedia data and classifying this information with associated objects is the primary step towards object recognition. Rasters play an important role while computing object boundary. The trade-off lies with the dimensionality of the object versus computational cost while achieving maximum efficiency. In th…
Beihang University（北京航空航天大学）；Polytechnic University of Milan（米兰理工大学）
Motion trajectory recognition is important for characterizing the moving property of an object. The speed and accuracy of trajectory recognition rely on a compact and discriminative feature representation, and the situations of varying rotation, scaling and translation has to be specially considered. In this paper we propose a novel feature extraction method for trajectories. Firstly a trajectory is represented by a proposed point context, which is a rotation-scale-translation (RST) invariant shape descriptor with a flexible tradeoff between computational complexity and discrimination, yet we …
University of Kufa（库法大学）；University of Babylon（巴比伦大学）
Diabetic Retinopathy is a medical condition where the retina is damaged because fluid leaks from blood vessels into the retina. The presence of hemorrhages in the retina is the earliest symptom of diabetic retinopathy. The number and shape of hemorrhages is used to indicate the severity of the disease. Early automated hemorrhage detection can help reduce the incidence of blindness. This paper introduced new method depending on the hemorrhage shape to detect the dot hemorrhage (DH), its number, and size at early stage, this can be achieved by reducing the retinal image details. Detection and re…
The current state-of-the-art hand gesture recognition methodologies heavily rely in the use of machine learning. However there are scenarios that machine learning cannot be applied successfully, for example in situations where data is scarce. This is the case when one-to-one matching is required between a query and a dataset of hand gestures where each gesture represents a unique class. In situations where learning algorithms cannot be trained, classic computer vision techniques such as feature extraction can be used to identify similarities between objects. Shape is one of the most important …
This paper presents a new axis-based shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that …
IMT Lille Douai（里尔杜埃国立高等矿业电信学院）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
The detection and tracking of human landmarks in video streams has gained in reliability partly due to the availability of affordable RGB-D sensors. The analysis of such time-varying geometric data is playing an important role in the automatic human behavior understanding. However, suitable shape representations as well as their temporal evolution, termed trajectories, often lie to nonlinear manifolds. This puts an additional constraint (i.e., nonlinearity) in using conventional Machine Learning techniques. As a solution, this paper accommodates the well-known Sparse Coding and Dictionary Lear…
Samsung Research America（三星美国研究院）；University of Notre Dame（圣母大学）
In this article, we analyze how changing the underlying 3D shape of the base identity in face images can distort their overall appearance, especially from the perspective of deep face recognition. As done in popular training data augmentation schemes, we graphically render real and synthetic face images with randomly chosen or best-fitting 3D face models to generate novel views of the base identity. We compare deep features generated from these images to assess the perturbation these renderings introduce into the original identity. We perform this analysis at various degrees of facial yaw with…
Few-shot Shape Recognition by Learning Deep Shape-aware Features
Southeast University（东南大学）；The Australian National University（澳大利亚国立大学）；University of Massachusetts, Dartmouth（马萨诸塞大学达特茅斯分校）；Data61/CSIRO（Data61/联邦科学与工业研究组织）
National Institute of Standards and Technology（美国国家标准与技术研究院）
In this paper, we investigate the use of 3D surface geometry for face recognition and compare it to one based on color map information. The 3D surface and color map data are from the CAESAR anthropometric database. We find that the recognition performance is not very different between 3D surface and color map information using a principal component analysis algorithm. We also discuss the different techniques for the combination of the 3D surface and color map information for multi-modal recognition by using different fusion approaches and show that there is significant improvement in results. …
This paper presents a novel method to recognize stem - calyx of an apple using shape descriptors. The main drawback of existing apple grading techniques is that stem - calyx part of an apple is treated as defects, this leads to poor grading of apples. In order to overcome this drawback, we proposed an approach to recognize stem-calyx and differentiated from true defects based on shape features. Our method comprises of steps such as segmentation of apple using grow-cut method, candidate objects such as stem-calyx and small defects are detected using multi-threshold segmentation. The shape featu…
Gait recognition, which identifies individuals based on their walking patterns, is an important biometric technique since it can be observed from a distance and does not require the subject's cooperation. Recognizing a person's gait is difficult because of the appearance variants in human silhouette sequences produced by varying viewing angles, carrying objects, and clothing. Recent research has produced a number of ways for coping with these variants. In this paper, we present the usage of inferring 3-D body shapes distilled from limited images, which are, in principle, invariant to the speci…
Shape analyses of tephra grains result in understanding eruption mechanism of volcanoes. However, we have to define and select parameter set such as convexity for the precise discrimination of tephra grains. Selection of the best parameter set for the recognition of tephra shapes is complicated. Actually, many shape parameters have been suggested. Recently, neural network has made a great success in the field of machine learning. Convolutional neural network can recognize the shape of images without human bias and shape parameters. We applied the simple convolutional neural network developed f…
3D shape representation and its processing have substantial effects on 3D shape recognition. The polygon mesh as a 3D shape representation has many advantages in computer graphics and geometry processing. However, there are still some challenges for the existing deep neural network (DNN)-based methods on polygon mesh representation, such as handling the variations in the degree and permutations of the vertices and their pairwise distances. To overcome these challenges, we propose a DNN-based method (PolyNet) and a specific polygon mesh representation (PolyShape) with a multi-resolution structu…
Object recognition in humans depends primarily on shape cues. We have developed a new approach to measuring the shape recognition performance of a vision system based on nearest neighbor view matching within the system's embedding space. Our performance benchmark, ShapeY, allows for precise control of task difficulty, by enforcing that view matching span a specified degree of 3D viewpoint change and/or appearance change. As a first test case we measured the performance of ResNet50 pre-trained on ImageNet. Matching error rates were high. For example, a 27 degree change in object pitch led ResNe…
There has been an extensive use of Unmanned Aerial Vehicles in search and rescue missions to distribute first aid kits and food packets. It is important that these UAVs are able to identify and distinguish the markers from one another for effective distribution. One of the common ways to mark the locations is via the use of characters superimposed on shapes of various colors which gives rise to wide variety of markers based on combination of different shapes, characters, and their respective colors. In this paper, we propose an object detection and classification pipeline which prevents false …
School of Computer Science and Software Engineering, The University of Western Australia（西澳大学计算机科学与软件工程学院）
This paper presents a novel personal identification and verification system using information extracted from the hand shape and texture. The system has two major constituent modules: a fully automatic and robust peg free segmentation and pose normalisation module, and a recognition module. In the first module, the hand is segmented from its background using a thresholding technique based on Otsu`s method combined with a skin colour detector. A set of fully automatic algorithms are then proposed to segment the palm and fingers. In these algorithms, the skeleton and the contour of the hand and f…
Arm ML Research Lab（Arm机器学习研究实验室）；Centre for Mathematical Sciences, Lund University（隆德大学数学科学中心）
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes inefficient as the set of input points grows larger. Furthermore, we find that the attention mechanism struggles to find useful connections between individual points on a global scale. In order to alleviate these problems, we propose a two-stage Point Transformer-in-Transformer (Point-TnT) approach which combines local and global attention mechanisms, enabling bot…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Berkeley（加州大学伯克利分校）
Early work in computer vision considered a host of geometric cues for both shape reconstruction and recognition. However, since then, the vision community has focused heavily on shading cues for reconstruction, and moved towards data-driven approaches for recognition. In this paper, we reconsider these perhaps overlooked "boundary" cues (such as self occlusions and folds in a surface), as well as many other established constraints for shape reconstruction. In a variety of user studies and quantitative tasks, we evaluate how well these cues inform shape reconstruction (relative to each other) i…
Talan（Talan公司）；Centrale Lille（里尔中央理工学院）；CNRS（法国国家科学研究中心）；EFREI PARIS（巴黎法国电子与计算机信息学院）；The Ohio State University（俄亥俄州立大学）
Deep Learning architectures, albeit successful in most computer vision tasks, were designed for data with an underlying Euclidean structure, which is not usually fulfilled since pre-processed data may lie on a non-linear space. In this paper, we propose a geometry aware deep learning approach for skeleton-based action recognition. Skeleton sequences are first modeled as trajectories on Kendall's shape space and then mapped to the linear tangent space. The resulting structured data are then fed to a deep learning architecture, which includes a layer that optimizes over rigid and non rigid trans…
Sapienza University（罗马第一大学）；University of Udine（乌迪内大学）；University of Bristol（布里斯托大学）
Estimating the 3D pose of a hand from a 2D image is a well-studied problem and a requirement for several real-life applications such as virtual reality, augmented reality, and hand gesture recognition. Currently, reasonable estimations can be computed from single RGB images, especially when a multi-task learning approach is used to force the system to consider the shape of the hand when its pose is determined. However, depending on the method used to represent the hand, the performance can drop considerably in real-life tasks, suggesting that stable descriptions are required to achieve satisfa…
Yonsei University（延世大学）；Korea University（高丽大学）；Korea Institute of Science and Technology (KIST)（韩国科学技术研究院）
We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D annotation. We accomplish this by representing an object as a composition of 3D shape and its appearance, while eliminating the effect of camera viewpoint, in a canonical configuration. Unlike conventional methods modeling spatial variation in 2D images only, our method is capable of reconfiguring the appearance feature in a canonical 3D space, thus enabling the subsequent object classifier to …
In this paper PREMONN (PREdictive MOdular Neural Networks) model/architecture is generalized to functions of two variables and to non-Euclidean spaces. It is presented in the context of 3D invariant shape recognition and texture recognition. PREMONN uses local relation, it is modular and exhibits incremental learning. The recognition process can start at any point on a shape or texture, so a reference point is not needed. Its local relation characteristic enables it to recognize shape and texture even in presence of occlusion. The analysis is mainly mathematical. However, we present some exper…
We present a novel approach to object classification and detection which requires minimal supervision and which combines visual texture cues and shape information learned from freely available unlabeled web search results. The explosion of visual data on the web can potentially make visual examples of almost any object easily accessible via web search. Previous unsupervised methods have utilized either large scale sources of texture cues from the web, or shape information from data such as crowdsourced CAD models. We propose a two-stream deep learning framework that combines these cues, with o…
In this paper we present our preliminary work on model-based behavioral analysis of horse motion. Our approach is based on the SMAL model, a 3D articulated statistical model of animal shape. We define a novel SMAL model for horses based on a new template, skeleton and shape space learned from $37$ horse toys. We test the accuracy of our hSMAL model in reconstructing a horse from 3D mocap data and images. We apply the hSMAL model to the problem of lameness detection from video, where we fit the model to images to recover 3D pose and train an ST-GCN network on pose data. A comparison with the sa…
We consider object detection using a generic model for natural shapes. A common approach for object recognition involves matching object models directly to images. Another approach involves building intermediate representations via a generic grouping processes. We argue that these two processes (model-based recognition and grouping) may use similar computational mechanisms. By defining a generic model for shapes we can use model-based techniques to implement a mid-level vision grouping process.
The motivation for using qualitative shape descriptions is as follows: qualitative shape descriptions can implicitly act as a schema for measuring the similarity of shapes, which has the potential to be cognitively adequate. Then, shapes which are similar to each other would also be similar for a pattern recognition algorithm. There is substantial work in pattern recognition and computer vision dealing with shape similarity. Here with our approach to qualitative shape descriptions and shape similarity, the focus is on achieving a representation using only simple predicates that a human could e…
DUT-RU International School of Information and Software Engineering, Dalian University of Technology（大连理工大学 DUT-RU 国际信息与软件学院）；Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province（辽宁省泛在网络与服务软件重点实验室）；School of Software, Dalian University of Technology（大连理工大学软件学院）
Recognizing freehand sketches with high arbitrariness is greatly challenging. Most existing methods either ignore the geometric characteristics or treat sketches as handwritten characters with fixed structural ordering. Consequently, they can hardly yield high recognition performance even though sophisticated learning techniques are employed. In this paper, we propose a sequential deep learning strategy that combines both shape and texture features. A coded shape descriptor is exploited to characterize the geometry of sketch strokes with high flexibility, while the outputs of constitutional ne…
Image recognition is the need of the hour. In order to be able to recognize an image, it is of immense importance that the image should be distinguishable from the background. In the present work, an approach is presented for automatic detection and recognition of regular 2D shapes in low noise environments. The work has a large number of direct applications in the real world. The algorithm proposed is based on locating the edges and thus, in turn calculating the area of the object helps in identification of a specified shape. The results were simulated using MATLAB tool are encouraging and va…
In convolutional neural network-based character recognition, pooling layers play an important role in dimensionality reduction and deformation compensation. However, their kernel shapes and pooling operations are empirically predetermined; typically, a fixed-size square kernel shape and max pooling operation are used. In this paper, we propose a meta-learning framework for pooling layers. As part of our framework, a parameterized pooling layer is proposed in which the kernel shape and pooling operation are trainable using two parameters, thereby allowing flexible pooling of the input data. We …
MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition
School of Electrical and Information Engineering, Tianjin University（天津大学电气与信息工程学院）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）
We investigate the problem of facial expression recognition using 3D data. Building from one of the most successful frameworks for facial analysis using exclusively 3D geometry, we extend the analysis from a curve-based representation into a spectral representation, which allows a complete description of the underlying surface that can be further tuned to the desired level of detail. Spectral representations are based on the decomposition of the geometry in its spatial frequency components, much like a Fourier transform, which are related to intrinsic characteristics of the surface. In this wo…
Handwritten automatic character recognition has attracted many researchers all over the world to contribute automatic character recognition domain. Shape identification and feature extraction is very important part of any character recognition system and success of method is highly dependent on selection of features. However feature extraction is the most important step in defining the shape of the character as precisely and as uniquely as possible. This is indeed the most important step and complex task as well and achieved success by using invariance property, irrespective of position and or…
Principal component analysis (PCA) is a popular tool for linear dimensionality reduction and feature extraction. Kernel PCA is the nonlinear form of PCA, which better exploits the complicated spatial structure of high-dimensional features. In this paper, we first review the basic ideas of PCA and kernel PCA. Then we focus on the reconstruction of pre-images for kernel PCA. We also give an introduction on how PCA is used in active shape models (ASMs), and discuss how kernel PCA can be applied to improve traditional ASMs. Then we show some experimental results to compare the performance of kerne…
Huazhong University of Science and Technology（华中科技大学）；Megvii (Face++) Inc.（旷视（Face++）公司）
Unifying text detection and text recognition in an end-to-end training fashion has become a new trend for reading text in the wild, as these two tasks are highly relevant and complementary. In this paper, we investigate the problem of scene text spotting, which aims at simultaneous text detection and recognition in natural images. An end-to-end trainable neural network named as Mask TextSpotter is presented. Different from the previous text spotters that follow the pipeline consisting of a proposal generation network and a sequence-to-sequence recognition network, Mask TextSpotter enjoys a sim…
Electronics and Telecommunications Research Institute (ETRI)（韩国电子通信研究院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
For the past decades, face recognition (FR) has been actively studied in computer vision and pattern recognition society. Recently, due to the advances in deep learning, the FR technology shows high performance for most of the benchmark datasets. However, when the FR algorithm is applied to a real-world scenario, the performance has been known to be still unsatisfactory. This is mainly attributed to the mismatch between training and testing sets. Among such mismatches, face misalignment between training and testing faces is one of the factors that hinder successful FR. To address this limitati…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
A longstanding question in computer vision concerns the representation of 3D shapes for recognition: should 3D shapes be represented with descriptors operating on their native 3D formats, such as voxel grid or polygon mesh, or can they be effectively represented with view-based descriptors? We address this question in the context of learning to recognize 3D shapes from a collection of their rendered views on 2D images. We first present a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and show that a 3D shape can be recognized even from a …
