Shape Analysis of Planar Multiply-Connected Objects Using Conformal Welding.

A new method for reconstructing the 3D shape of single cells in fruit

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.

We used functional magnetic resonance imaging to investigate the human cortical areas involved in processing 3-dimensional (3D) shape from texture (SfT) and shading. The stimuli included monocular images of randomly shaped 3D surfaces and a wide variety of 2-dimensional (2D) controls. The results of both passive and active experiments reveal that the extraction of 3D SfT involves the bilateral caudal inferior temporal gyrus (caudal ITG), lateral occipital sulcus (LOS) and several bilateral sites along the intraparietal sulcus. These areas are largely consistent with those involved in the processing of 3D shape from motion and stereo. The experiments also demonstrate, however, that the analysis of 3D shape from shading is primarily restricted to the caudal ITG areas. Additional results from psychophysical experiments reveal that this difference in neuronal substrate cannot be explained by a difference in strength between the 2 cues. These results underscore the importance of the posterior part of the lateral occipital complex for the extraction of visual 3D shape information from all depth cues, and they suggest strongly that the importance of shading is diminished relative to other cues for the analysis of 3D shape in parietal regions.

There is a growing interest in shape analysis in recent years. We present a novel shape signature for 2D bounded simply-connected domains, named the Harmonic Beltrami signature (HBS). The proposed signature is based on the harmonic extension of the conformal welding map of a unit circle and its Beltrami coefficient. We show that there is a one-to-one correspondence between the quotient space of HBS and the space of 2D simply-connected shapes up to a translation, rotation and scaling. With a suitable normalization, each equivalence class in the quotient space of HBS is associated to a unique representative. It gets rid of the conformal ambiguity. As such, each shape is associated to a unique HBS. Conversely, the associated shape of a HBS can be reconstructed based on quasiconformal Teichmuller theories, which is uniquely determined up to a translation, rotation and scaling. The HBS is thus an effective fingerprint to represent a 2D shape. The robustness of HBS is studied both theoretically and experimentally. With the HBS, simple metric, such as L2, can be used to measure geometric dissimilarity between shapes. Experiments have been carried out to classify shapes in different classes using HBS. Results show good classification performance, which demonstrate the efficacy of our proposed shape signature.

The Multi-view Convolution Neural Network (MVCNN) has achieved considerable success in 3D shape recognition. However, 3D shape recognition using view-images from random viewpoints has not been yet exploited in depth. In addition, 3D shape recognition using a small number of view-images remains difficult. To tackle these challenges, we developed a novel Multi-view Convolution Neural Network, “Latent-MVCNN” (LMVCNN), that recognizes 3D shapes using multiple view-images from pre-defined or random viewpoints. The LMVCNN consists of three types of sub Convolution Neural Networks. For each view-image, the first type of CNN outputs multiple category probability distributions and the second type of CNN outputs a latent vector to help the first type of CNN choose the decent distribution. The third type of CNN outputs the transition probabilities from the category probability distributions of one view to the category probability distributions of another view, which further helps the LMVCNN to find the decent category probability distributions for each pair of view-images. The three CNNs cooperate with each other to the obtain satisfactory classification scores. Our experimental results show that the LMVCNN achieves competitive performance in 3D shape recognition on ModelNet10 and ModelNet40 for both the pre-defined and the random viewpoints and exhibits promising performance when the number of view-images is quite small.

I propose novel 3D shape analysis and modeling algorithm for active contours using variational scheme. The proposed algorithm utilizes an unknown surface of 3D shape by normal to 3D shape analysis and modeling. It would be used to get high quality reconstruction's results from many dimensions' data. I give it by utilizing continuous anisotropism weights would finish comparable ameliorate to surface reconstruction.

Accurate image moment computation is critical because they are used in a variety of fields, including image reconstruction and object recognition. Orthogonal polynomials are frequently used to compute moments due to their numerous intersecting and important theoretical properties. In polar coordinate systems, orthogonal polynomials such as the Polar Harmonic Fourier Transform (PHFT) and Polar Harmonic Transformation (PHT) are defined. However, the images are defined by a Cartesian coordinate system. To obtain image moments, a double integration over a unit circle over the product of the PHFT or PHT and the image function must be performed. The choice of double integration techniques and domain for the double integral has a significant effect on the precision of the computed moments. We have proposed a method for using the entire unit circle as an integration domain in this study, for image reconstruction. We used the PHFT and PHT to apply this technique to computing moments for the reconstruction. The proposed method outperforms other state-of-the-art methods, including Gaussian quadrature numerical integration method (GQM) and zeroth order approximation (ZOA) on variety of scenarios using three benchmarked image sets. We have demonstrated experimentally that this technique significantly improves the accuracy of image moments in higher order moments, as measured by reduced mean squared error (MSE). Additionally, the proposed method significantly improved the moment’s rotational (an improvement of 1-3% as compared to GQM and an improvement of 37-93% as compared to ZOA) and scaling invariance (an improvement of 0-500% as compared to GQM and an improvement of 3-7000% as compared to ZOA).

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

During development and tissue repair, cells reshape and reconfigure to ensure organs take specific shapes. This process is inherently three-dimensional (3D). Yet, in part due to limitations in imaging and data analysis, cell shape analysis within tissues has largely been studied in two-dimensions (2D), e.g., the Drosophila wing disc. With recent advances in imaging and machine learning, there has been significant progress in our understanding of 3D cell and tissue shape in vivo. However, even after gaining 3D segmentation of cells, it remains challenging to extract cell shape metrics beyond volume and surface area for cells within densely packed tissues. To address the challenge of extracting 3D cell shape metrics from dense tissues, we have developed the Python package CellMet. This user-friendly tool enables extraction of quantitative shape information from 3D cell and tissue segmentations, including cell face properties, cell twist, and cell rearrangements in 3D. Our method will improve the analysis of 3D cell shape and the understanding of cell organisation within tissues. Our tool is open source, available at https://github.com/TimSaundersLab/CellMet.

3D shape recognition is a critical research topic in the field of computer vision, attracting substantial attention. Existing approaches mainly focus on extracting distinctive 3D shape features; however, they often neglect the model’s robustness and lack refinement in deep features. To address these limitations, we propose the point-view fusion attention network that aims to extract a concise, informative, and robust 3D shape descriptor. Initially, our approach combines multi-view features with point cloud features to obtain accurate and distinguishable fusion features. To effectively handle these fusion features, we design a dual-attention convolutional network which consists of a channel attention module and a spatial attention module. This dual-attention mechanism greatly enhances the generalization ability and robustness of 3D recognition models. Notably, we introduce a strip-pooling layer in the channel attention module to refine the features, resulting in improved fusion features that are more compact. Finally, a classification process is performed on the refined features to assign appropriate 3D shape labels. Our extensive experiments on the ModelNet10 and ModelNet40 datasets for 3D shape recognition and retrieval demonstrate the remarkable accuracy and robustness of the proposed method.

In recent years, the zero-shot image recognition with semantic knowledge has achieved good performance due to vision-language models. However, because of the complexity of 3D shapes, the model cannot fully use the semantic knowledge of 3D shapes, which results in low accuracy of zero-shot 3D shape recognition. To address this problem, we propose a Semantic-enhanced ULIP for Zero-shot 3D Shape Recognition (SE-ULIP). This method utilizes the contrastive learning to fine-tune the text encoder in two stages, including the domain adaptation fine-tuning and the triplets-based text encoder fine-tuning. In the domain adaptation fine-tuning, we fine-tune the image encoder and the text encoder using the views and the Semantic Descriptive Text (SDT) of each view generated by the Visual Question Answering (VQA) model, which aims to align the view features with the semantic knowledge. In the triplets-based text encoder fine-tuning, we propose an Adaptive Conditional Adjustment Context Optimization (ACACoOp) to learn the optimal context vectors. The optimal context vectors are used as the input to fine-tune the text encoder again, which enhance SE-ULIP to understand the semantic knowledge of 3D shapes. Experiments show that our method achieves the state-of-the-art performance through the fine-tuned text encoder on three 3D backbone networks for both zero-shot and standard 3D shape recognition.

The classification of urban landscape in aerial lidar point clouds is useful in 3D modeling and object recognition applications in urban environments. In this paper, we introduce a multi-category classification system for identifying water, ground, roof, and trees in airborne lidar. The system is organized as a cascade of binary classifiers, each of which performs unsupervised region growing followed by supervised, segment-wise classification. Categories with the most discriminating features, such as water and ground, are identified first and are used as context for identifying more complex categories, such as trees. We use 3D shape analysis and region growing to identify ¿planar¿ and ¿scatter¿ regions that likely correspond to ground/roof and trees respectively. We demonstrate results on two urban datasets, the larger of which contains 200 million lidar returns over 7km <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> . We show that our ground, roof, and tree classifiers, when trained on one dataset, perform well on the other dataset.

This paper concerns a topics studied by many researchers around the world: 3D object recognition from vision. In our robotics context,an object must be recognized and localized in order to be grasped by a mobile robot equipped with a manipulator arm Mitsubishi PA10-6C: several cameras are mounted on this robot, on a static mast or on the wrist of the arm. The use of such a robot for object recognition, makes possible active strategies for object recognition. This system must be able to place the sensor in different positions around the object in order to learn discriminant features on every object to be recognized in a first step, and then to recognize these objects before a grasping task. Our method exploits the Mutual Information to actively acquire visual data until the recognition, like it was proposed in works presented in (?) and (Denzler et al., 2001): color histogram, shape context, shape signature ,interest points harris et sift descriptors are learnt from different viewpoint around every object in order to make the system more robust and efficient.

We present a new method for computing the shape similarity between 3D polygonal models using an informationtheoretic viewpoint selection framework. Given a 3D model, a sphere of viewpoints surrounding this model is used to obtain its shape signature from the mutual information of each viewpoint. This signature represents the essence of the shape from a view-based approach. Then, in order to quantify the dissimilarity between two models, their mutual information spheres are registered by minimizing the L2 distance between them. Several experiments show the discrimination capabilities of our approach and its potential suitability for object recognition.

Image classification and retrieval has significant importance in a wide variety of applications like object recognition, tracking, and content based retrieval, etc. Images usually consist of various objects which are segmented and then analysed for object-based classification and recognition. Owing to the absence of intensity and colour information, binary objects are difficult to recognise. They are usually represented using compact, geometrically invariant and robust features extracted from the object's contour or interior region. These features form the basis for recognition and govern the overall performance of classification systems. A new shape signature is introduced in this paper for representing shapes through angular profiles signature which are extracted from objects enclosed within minimum bounding circles. We have evaluated the discriminatory capabilities of this signature in shape recognition and retrieval on two shape datasets. Experimental results indicate that the signature is able to represent shapes effectively, achieving overall accuracy of 94%.