Search

The domain of remote sensing image processing has witnessed remarkable advancements in recent years, with deep convolutional neural networks (CNNs) establishing themselves as a prominent approach for building segmentation. Despite the progress, traditional CNNs, which rely on convolution and pooling for feature extraction during the encoding phase, often fail to precisely delineate global pixel interactions, potentially leading to the loss of vital semantic details. Moreover, conventional CNN-based segmentation models frequently neglect the nuanced semantic differences between shallow and deep features during the decoding phase, which can result in subpar feature integration through rudimentary addition or concatenation techniques. Additionally, the unique boundary characteristics of buildings in remote sensing images, which offer a rich vein of prior information, have not been fully harnessed by traditional CNNs. This paper introduces an innovative approach to building segmentation in remote sensing images through a prior-guided dual branch multi-feature fusion network (PDBMFN). The network is composed of a prior-guided branch network (PBN) in the encoding process, a parallel dilated convolution module (PDCM) designed to incorporate prior information, and a multi-feature aggregation module (MAM) in the decoding process. The PBN leverages prior region and edge information derived from superpixels and edge maps to enhance edge detection accuracy during the encoding phase. The PDCM integrates features from both branches and applies dilated convolution across various scales to expand the receptive field and capture a more comprehensive semantic context. During the decoding phase, the MAM utilizes deep semantic information to direct the fusion of features, thereby optimizing segmentation efficacy. Through a sequence of aggregations, the MAM gradually merges deep and shallow semantic information, culminating in a more enriched and holistic feature representation. Extensive experiments are conducted across diverse datasets, such as WHU, Inria Aerial, and Massachusetts, revealing that PDBMFN outperforms other sophisticated methods in terms of segmentation accuracy. In the key segmentation metrics, including mIoU, precision, recall, and F1 score, PDBMFN shows a marked superiority over contemporary techniques. The ablation studies further substantiate the performance improvements conferred by the PBN's prior information guidance and the efficacy of the PDCM and MAM modules. [ABSTRACT FROM AUTHOR]

Accurate and robust 3D human modeling from a single image presents significant challenges. Existing methods have shown potential, but they often fail to generate reconstructions that match the level of detail in the input image. These methods particularly struggle with loose clothing. They typically employ parameterized human models to constrain the reconstruction process, ensuring the results do not deviate too far from the model and produce anomalies. However, this also limits the recovery of loose clothing. To address this issue, we propose an end-to-end method called IHRPN for reconstructing clothed humans from a single 2D human image. This method includes a feature extraction module for semantic extraction of image features. We propose an image semantic feature extraction aimed at achieving pixel model space consistency and enhancing the robustness of loose clothing. We extract features from the input image to infer and recover the SMPL-X mesh, and then combine it with a normal map to guide the implicit function to reconstruct the complete clothed human. Unlike traditional methods, we use local features for implicit surface regression. Our experimental results show that our IHRPN method performs excellently on the CAPE and AGORA datasets, achieving good performance, and the reconstruction of loose clothing is noticeably more accurate and robust. [ABSTRACT FROM AUTHOR]

Transferring a photo to a stylised image with beautiful texture has become one of the most popular topics in computer vision and the application of image processing. Controlling the stroke size of the texture is one of the challenging problems in this task. Recent representative methods for such problem introduce a pyramid model to regulate receptive fields in the network. Meanwhile, dilated convolutions are proved to be a very efficient way to adjust receptive fields without losing resolution. By combining the advantages of both approaches and making special optimisation for VGG19 model for style transfer tasks, the authors propose to exploit dilated convolutions to extract texture information endowing the network with stroke controllable. Several sets of contrast experiments were conducted and results show that their algorithm can generate more attractive stylisation images and control stroke size flexibly. It demonstrates the superiority of applying dilated convolutions as a texture extraction method for maintaining more texture information and controlling stroke size. [ABSTRACT FROM AUTHOR]

With regard to the numerous complex holes that accompany a three-dimensional (3D) model reconstruction, a hole-repair method is proposed in this paper. First, signed distance function (SDF) is constructed, and the curved surface where the hole is positioned is expressed by a static SDF. Another dynamic SDF is used to express the initial curved surface. Using a variation level set on implicit surfaces, we introduce a global convex optimization energy model to perform minimum inducement, thus turning the problem of extracting the hole edge into a problem of spherical evolution of a hidden surface. Finally, we consider the extracted hole-edge surface as the initial observation surface and complete the hole repair using convolution and synthesis. The experiment shows that this algorithm can effectively restore notable geometrical features of areas with complex holes and can repair the holes in a model with many grids. [ABSTRACT FROM AUTHOR]

• We propose a representation of 3D landmarks set. • We propose a measure method for landmarks in the Kendall shape space. • We propose an ethnicity classification method. Knowledge of human ethnicity constitutes important biometric information. An automated ethnicity classification is a good first step in facial analysis. However, most ethnicity classification methods require a complex feature extraction and model training process. We propose a novel ethnicity classification method based on the analysis of facial landmarks in Kendall shape space. Facial features with different relative positions have a close relationship with ethnicity. Facial landmarks can represent positions of facial features. We build a Discrete Landmarks Model (DLM) based on facial landmarks and construct an ethnicity classification model based on the DLM analysis. The clear advantages of our method are that it is fully automated; requires no complex data preprocessing, feature extraction or a complex training process; results in a fast and accurate classification process. We estimate the effectiveness of our method experimentally, using public databases such as Texas3D, FRGC2.0, BU-3DFE and BU-4DFE. On average, our method can achieve a 95% ethnicity classification rate with each classification attempt in 2.0 s. [ABSTRACT FROM AUTHOR]

• We propose a feature ponits selection method on 3D craniofacial models, which result in automatic and stable feature landmark extraction. • We propose a new craniofacial registration framework using radial curves and our extracted landmarks. Our registration is automatic and effective. • We perform extensive experiments on craniofacial data registration and demonstrate the effectiveness of this radial curve based registration. Accurate registration of three-dimensional craniofacial surface is a foundation for craniofacial reconstruction. Most of craniofacial registration methods need to manually calibrate the feature points. This paper presents an automatic craniofacial registration method based on radial curves. First, we extract radial curves on both the reference and target craniofacial surfaces, and suggest an automatic feature point selection algorithms on these radial curves. Second, we align the two sets of radial curves, and develop a consistency point drift (CPD) algorithm to establish correspondences between feature points on the reference and target surfaces. Then, these feature points are used as control points of the thin plate spline transformation (TPS) algorithm, and the reference craniofacial surface is transformed toward the target craniofacial surface. Finally, the corresponding points of the reference surface on the target surface are searched to realize the registration. The experimental results show that the proposed algorithm is effective. [ABSTRACT FROM AUTHOR]