Deep implicit functions (DIFs) effectively represent shapes by using a neural network to map 3D spatial coordinates to scalar values that encode the shape's geometry, but it is difficult to establish correspondences between shapes directly, limiting their use in medical image registration. The recently presented deformation field-based methods achieve implicit templates learning via template field learning with DIFs and deformation field learning, establishing shape correspondence through deformation fields. Although these approaches enable joint learning of shape representation and shape correspondence, the decoupled optimization for template field and deformation field, caused by the absence of deformation annotations lead to a relatively accurate template field but an underoptimized deformation field. In this paper, we propose a novel implicit template learning framework via a shared hybrid diffeomorphic flow (SHDF), which enables shared optimization for deformation and template, contributing to better deformations and shape representation. Specifically, we formulate the signed distance function (SDF, a type of DIFs) as a one-dimensional (1D) integral, unifying dimensions to match the form used in solving ordinary differential equation (ODE) for deformation field learning. Then, SDF in 1D integral form is integrated seamlessly into the deformation field learning. Using a recurrent learning strategy, we frame shape representations and deformations as solving different initial value problems of the same ODE. We also introduce a global smoothness regularization to handle local optima due to limited outside-of-shape data. Experiments on medical datasets show that SHDF outperforms state-of-the-art methods in shape representation and registration.

Visible-infrared person re-identification (VI-ReID) aims to match person images of the same identity across different modalities. To mitigate the non-linear differences between visible and infrared modalities, we propose the Contour-Guided Modality Mitigation Network(CGMMNet), which integrates middle modality(M-modality) images and contour maps into the network. The M-modality images mitigate the color differences between the two modalities, while the contour maps compensate for the blurred human body boundaries in both original and M-modality images. To leverage these characters, we employ a contour fusion module to densely integrate contour features with image features, and define an energy function to further enhance the representation of contour information. Additionally, we designed a multi-scale feature co-learning module that partitions the extracted features into dual-granularity local features and mitigates the semantic loss caused by rigid horizontal partitioning through a soft prediction consistency constraint. Extensive experiments on SYSU-MM01 and RegDB datasets demonstrate the effectiveness of CGMMNet.

3D point cloud is often affected by sensor noise, environmental interference, and incomplete collection, resulting in noise, missing, and anomalies in the point cloud. Existing work in handling such data primarily focuses on the coordinate information of the point cloud, overlooking its local structure and the interrelation between points, thereby reducing the accuracy of model predictions. To enhance the ability to capture point cloud features, we propose a high-precision and robust 3D point cloud analysis model called PointMLFF. Specifically, we introduce a 3D surface-based point local feature extractor, capturing the local geometric features of the point cloud by approximating the Taylor series to construct local spatial geometries. This method preserves both the absolute position information and the local shape information of the point cloud. Additionally, we propose a multi-level key-point attention module based on deep features, which constructs a point embedding space capable of perceiving abnormal changes in the point cloud by calculating the key-neighbor point attention and inter-key point attention in the feature space, significantly improving the model’s robustness. Extensive experiments show that PointMLFF outperforms most advanced methods in various downstream tasks. Notably, our method achieves a high classification accuracy of 88.9% on the challenging ScanObjectNN and surpasses others on abnormal point clouds. The visualization of partial segmentation results closely resembles the actual scenarios.

Acquiring semantics directly from a point cloud is an important requirement for handling point cloud tasks. However, point clouds captured with laser scanner equipment are often incomplete due to the limitations posed by target occlusion and light reflection. Consequently, recovering the complete point clouds from partial and sparse ones is essential for further studies. In this paper, we model a novel projected generative adversarial network (PGAN) for point cloud completion. First, we present a multi-scale generator module (MSGM) to fully capture the local structures and global shape in the raw incompletion point cloud and generate the multi-scale complete point cloud. In contrast to existing point cloud feature extractors, our MSGM promotes a correlation between different regions of an incomplete point cloud and integrates the contextual information of the point cloud. Second, we observe that the existing point discriminator is inadequate to enhance the discrimination of the prediction point cloud. To address this problem, we project the completed point cloud to 2D maps and apply adversarial training to discriminate the geometrical shape from a specific viewpoint. Comprehensive experiments on the ShapeNet and ModelNet40 datasets show that the proposed method performs well against existing point cloud completion tasks. We also present an ablation study to demonstrate the advantages of the projected generative adversarial network.

In recent years, underwater image enhancement methods based on deep learning have achieved remarkable results. Since the images obtained in complex underwater scenarios lack a ground truth, these algorithms mainly train models on underwater images synthesized from in-air images. Synthesized underwater images are different from real-world underwater images; this difference leads to the limited generalizability of the training model when enhancing real-world underwater images. In this work, we present an underwater image enhancement method that does not require training on synthetic underwater images and eliminates the dependence on underwater ground-truth images. Specifically, a novel domain adaptation framework for real-world underwater image enhancement inspired by transfer learning is presented; it transfers in-air image dehazing to real-world underwater image enhancement. The experimental results on different real-world underwater scenes indicate that the proposed method produces visually satisfactory results.

Motivated by the fact that the medial axis transform is able to encode the shape completely, we propose to use as few medial balls as possible to approximate the original enclosed volume by the boundary surface. We progressively select new medial balls, in a top-down style, to enlarge the region spanned by the existing medial balls. The key spirit of the selection strategy is to encourage large medial balls while imposing given geometric constraints. We further propose a speedup technique based on a provable observation that the intersection of medial balls implies the adjacency of power cells (in the sense of the power crust).We further elaborate the selection rules in combination with two closely related applications. One application is to develop an easy-to-use ball-stick modeling system that helps non-professional users to quickly build a shape with only balls and wires, but any penetration between two medial balls must be suppressed. The other application is to generate porous structures with convex, compact (with a high isoperimetric quotient) and shape-aware pores where two adjacent spherical pores may have penetration as long as the mechanical rigidity can be well preserved.

The detection of 3D interest points is a central problem in computer graphics, computer vision, and pattern recognition. It is also an important preprocessing step in the analysis of 3D model matching. Although studied for decades, detecting 3D interest points remains a challenge. In this study, a novel multiscale bilateral filtering method is presented to detect 3D interest points. This method first simplifies repeatedly the input 3D mesh to form k multiresolution meshes. For each mesh, on the basis of the computed saliency of the mesh vertex, the bilateral filtering is used to remove the noise of the mesh saliencies and the global contrast to normalise the saliencies, and then the interest points are extracted on the basis of the normalised saliency. The proposed method then gathers and clusters all interest points detected on the k multiresolution meshes, and the centres of these clusters are treated as the final interest points. In this method, both the spatial closeness and the geometric similarities of the mesh vertices are considered during the bilateral filtering process. The experimental results validate the effectiveness of the proposed method to detect 3D interest points. This method is also tested the potential to distinguish 3D models.

Point set registration is a fundamental problem in many domains of computer vision. In previous work on the registration, the point sets are often represented using Gaussian mixture models and the registration process is represented as a form of a probabilistic solution. For non‐rigid point set registration, however, the asymmetric Gaussian (AG) model can capture spatially asymmetric distributions compared with symmetric Gaussian, and the structural feature of the point sets reserve relatively complete and has important significance in registration. In this work, the authors designed a new shape context (SC) descriptor which combines the local and global structures of the point set. Meanwhile, they proposed a non‐rigid point set registration algorithm which formulates a registration process as the mixture probability density estimation of the AG mixture model, and the method introduce the structural feature by the new SC. Extensive experiments show that the proposed algorithm has a clear improvement over the state‐of‐the‐art methods.

Content‐based image retrieval (CBIR) is a research hotspot. To improve the performance of a CBIR system, especially the retrieval accuracy, this work proposes a method that uses a soft hypergraph combined with a weighted adjacent structure (WAS) to retrieve images. In this method, the similarities between images are computed and a similarity matrix is constructed by a conjoined colour difference histogram and micro‐structure descriptor method. Furthermore, a novel WAS and a soft hypergraph model are utilised to further improve the retrieval precision. The proposed method is compared with other methods in several datasets. Experimental results manifest the performance and robustness of this proposed method.

Graphic matching is a very critical issue in all aspects of computer vision. In this paper, a new graphics matching algorithm combining shape contexts and reweighted random walks was proposed. On the basis of the local descriptor, shape contexts, the reweighted random walks algorithm was modified to possess stronger robustness and correctness in the final result. Our main process is to use the descriptor of the shape contexts for the random walk on the iteration, of which purpose is to control the random walk probability matrix. We calculate bias matrix by using descriptors and then in the iteration we use it to enhance random walks’ and random jumps' accuracy, finally we get the one-to-one registration result by discretization of the matrix. The algorithm not only preserves the noise robustness of reweighted random walks but also possesses the rotation, translation, scale invariance of shape contexts. Through extensive experiments, based on real images and random synthetic point sets, and comparisons with other algorithms, it is confirmed that this new method can produce excellent results in graphic matching.

The hydration of Portland cement paste has an important impact on the formation of microstructure and development of strength. Manual derivation of cement hydration kinetic equation is very difficult because of the extreme complexity in Portland cement hydration. It can be reversely extracted automatically from the observed time series using evolutionary computation method. However, the physical meaning of coefficients of the extracted kinetic equation can not be understood easily, which limits the scope of application of kinetic equation in predicting hydration reaction. In this paper, in order to predict the reaction process of Portland cement, an evolutionary approach to predict the development of cement hydration using extreme early-age data and differential evolution algorithm is proposed. The experimental results indicate that the proposed method is very suitable for the forecasting of the development of degree of hydration for Portland cement.