Plant 3D reconstruction plays a critical role in precision agriculture and plant growth monitoring, yet it faces challenges such as complex background interference, difficulties in capturing intricate plant structures, and a slow reconstruction speed. In this study, we propose PlantSamGaussianReconstruction (PSGR), a novel method that integrates Grounding SAM with 3D Gaussian Splatting (3DGS) techniques. PSGR employs Grounding DINO and SAM for accurate plant–background segmentation, utilizes algorithms such as Scale-Invariant Feature Transform (SIFT) for camera pose estimation and sparse point cloud generation, and leverages 3DGS for plant reconstruction. Furthermore, a 3D–2D projection-guided optimization strategy is introduced to enhance segmentation precision. The experimental results of various multi-view plant image datasets demonstrate that PSGR effectively removes background noise under diverse environments, accurately captures plant details, and achieves peak signal-to-noise ratio (PSNR) values exceeding 30 in most scenarios, outperforming the original 3DGS approach. Moreover, PSGR reduces training time by up to 26.9%, significantly improving reconstruction efficiency. These results suggest that PSGR is an efficient, scalable, and high-precision solution for plant modeling.

When presented with one or a few photos of a previously unseen object, humans can instantly recognize it in different scenes. Although the human brain mechanism behind this phenomenon is still not fully understood, this work introduces a novel technical realization of this task. It consists of two phases: (1) generating a Similarity Density Map (SDM) by convolving the scene image with the given object image patch(es) so that the highlight areas in the SDM indicate the possible locations; (2) obtaining the object occupied areas in the scene through a Region Alignment Network (RAN). The RAN is constructed on a backbone of Deep Siamese Network (DSN), and different from the traditional DSNs, it aims to obtain the object accurate regions by regressing the location and area differences between the ground truths and the predicted ones indicated by the highlight areas in SDM. By pre-learning from labels annotated in traditional datasets, the SDM-RAN can detect previously unknown objects without fine-tuning. Experiments were conducted on the MS COCO, PASCAL VOC datasets. The results indicate that the proposed method outperforms state-of-the-art methods on the same task.

Accurate virtual orbital reconstruction is crucial for preoperative planning. Traditional methods, such as the mirroring technique, are unsuitable for orbital defects involving both sides of the midline and are time-consuming and labor-intensive. This study introduces a modified 3D U-Net+++ architecture for orbital defects reconstruction, aiming to enhance precision and automation. The model was trained and tested with 300 synthetic defects from cranial spiral CT scans. The method was validated in 15 clinical cases of orbital fractures and evaluated using quantitative metrics, visual assessments, and a 5-point Likert scale, by 3 surgeons. For synthetic defect reconstruction, the network achieved a 95% Hausdorff distance (HD95) of<2.0 mm, an average symmetric surface distance (ASSD) of ∼0.02 mm, a surface Dice similarity coefficient (Surface DSC)>0.94, a peak signal-to-noise ratio (PSNR)>35 dB, and a structural similarity index (SSIM)>0.98, outperforming the compared state-of-the-art networks. For clinical cases, the average 5-point Likert scale scores for structural integrity, edge consistency, and overall morphology were>4, with no significant difference between unilateral and bilateral/trans-midline defects. For clinical unilateral defect reconstruction, the HD95 was ∼2.5 mm, ASSD<0.02 mm, Surface DSC>0.91, PSNR>30 dB, and SSIM>0.99. The automatic reconstruction process took ∼10 seconds per case. In conclusion, this method offers a precise and highly automated solution for orbital defect reconstruction, particularly for bilateral and trans-midline defects. We anticipate that this method will significantly assist future clinical practice.

Real-time object detection remains an important topic in computer vision. Balancing the accuracy and speed of object detectors is a formidable challenge for both academic researchers and industry practitioners. In this paper, considering the latest models may be somewhat over-optimized for anchor-free pipes, we elect to use YOLOX as our baseline and introduce a series of enhancements, forming in a new high-performance detector named YOLOAX. To further exploit the power of the attention mechanism, we devise multi-dimensional attention-based modules which can activate CNNs, emphasizing regions of interest and boosting the capacity to learn the informative representations from feature maps. Moreover, we introduce a new label assignment strategy called STA, along with a novel loss function named GEIOU Loss, to further refine our object detector’s performance. Extensive ablation studies on the COCO and PASCAL VOC 2012 datasets are provided to validate our proposed methods. Our YOLOAX series is trained solely on the COCO dataset from scratch, without any prior knowledge, surpassing YOLOX series by a margin of 4.0% AP. Especially, YOLOAX-X achieves an impressive 55.2% AP on the COCO 2017 test set while maintaining a real-time speed of 82.4 fps.

OBJECTIVE:To establish a high-precision, automated model using deep learning for the fine classification and three-dimensional (3D) segmentation of mixed dentition in cone-beam computed tomography (CBCT) images. METHODS:A high-precision, automated deep learning model was built based on modified nnU-Net and U-Net networks and was used to classify and segment mixed dentition. It was trained on a series of 336 CBCT scans and tested using 120 mixed dentition CBCT scans from three centers and 143 permanent dentition CBCT scans from a public dataset. The diagnostic performance of the model was assessed and compared with those of two observers with different seniority levels. RESULTS:The model achieved accurate classification and segmentation of specific tooth positions in the internal and external mixed dentition datasets (Dice similarity coefficient: 0.964 vs. 0.951; Jaccard coefficient: 0.931 vs. 0.921; precision: 0.963 vs. 0.945; recall: 0.945 vs. 0.941; F-1 score: 0.954 vs. 0.943). These indices consistently exceeded 0.9 across multiple conditions, including fillings, malocclusion, and supernumerary tooth, with an average symmetric surface distance of 0.091 ± 0.029 mm. For permanent dentition, the Dice similarity and Jaccard coefficients exceeded 0.90, the average symmetric surface distance was 0.190 ± 0.092 mm, and precision and recall exceeded 0.94. With the aid of the model, the performance of junior dentists in mixed dentition classification and segmentation improved significantly; in contrast, there was no significant improvement in the performance of senior dentists. The speed of segmentation conducted by the dentists increased by 20.9-22.8 times. CONCLUSION:The artificial intelligence model has strong clinical applicability, robustness, and generalizability for mixed and permanent dentition. CLINICAL SIGNIFICANCE:The precise classification and 3D segmentation of mixed dentition in dentofacial deformities, supernumerary teeth, and metal artifacts present challenges. This study developed a deep learning approach to analyze CBCT scans, enhancing diagnostic accuracy and efficacy. It facilitates detailed measurements of tooth morphology and movement as well as informed orthodontic planning and orthotic design. Additionally, this method supports dental education by assisting doctors in explaining CBCT images to the families of pediatric patients.

Building extraction from high-resolution remote sensing images benefits various practical applications. However, automation of this process is challenging due to the variety of building surface coverings, complex spatial layouts, different types of structures, and tree occlusion. In this study, we propose a multilayer perception network for building extraction from high-resolution remote sensing images. By constructing parallel networks at different levels, the proposed network retains spatial information of varying feature resolutions and uses the parsing module to perceive the prominent features of buildings, thus enhancing the model's parsing ability to target scale changes and complex urban scenes. Further, a structure-guided loss function is constructed to optimize building extraction edges. Experiments on multi-source remote sensing data sets show that our proposed multi-level perception network presents a superior performance in building extraction tasks.

At present, most of the networks used to extract features in tracking algorithms are pre-trained on the ImageNet classification data set, such as VGG-16, AlexNet, etc. Most of the features used are feature maps output by the highest convolutional layer, so as to make full use of the powerful expressive power of convolutional features. But it will bring certain problems. The spatial resolution ability of convolutional neural network is not strong. If the target moves fast, exceeds the sampling area of the picture, or the target is occluded by background objects, the target tracking algorithm will fail. In order to further improve the spatial resolution ability of the convolutional neural network and solve the problem of tracking failure that may be caused by local cutting, a single target tracking algorithm based on feature fusion is proposed here. The feature map of the last layer is up-sampled and merged with the feature map of the previous layer to improve the spatial resolution ability. At the same time, the information of different feature models is used to improve the accuracy of the tracking algorithm. In addition to the local detection model, this article also proposes a classification detection model. When the local detection model cannot perform effective detection, multiple detection models are used instead to detect within the entire image to find the location where the target may appear. If the location where the target appears is found, the local detection model continues to be used at that location.

Deep learning has become an active research topic in the field of medical image analysis. In particular, for the automatic segmentation of stomatological images, great advances have been made in segmentation performance. In this paper, we systematically reviewed the recent literature on segmentation methods for stomatological images based on deep learning, and their clinical applications. We categorized them into different tasks and analyze their advantages and disadvantages. The main categories that we explored were the data sources, backbone network, and task formulation. We categorized data sources into panoramic radiography, dental X-rays, cone-beam computed tomography, multi-slice spiral computed tomography, and methods based on intraoral scan images. For the backbone network, we distinguished methods based on convolutional neural networks from those based on transformers. We divided task formulations into semantic segmentation tasks and instance segmentation tasks. Toward the end of the paper, we discussed the challenges and provide several directions for further research on the automatic segmentation of stomatological images.

The traditional Siamese network-based target tracking algorithm needs to use the convolution feature of the target to scan around the target location when predicting the location of the target in the next frame image, and perform similarity calculation to obtain the similarity score matrix with the highest score. It is the next frame target position. The highest similarity score often does not represent the precise target position of the target, which is often affected by the sliding step size during scanning. Aiming at this problem, this paper proposes a target tracking method based on density clustering. By combining the Siamese network to predict the next frame target position, and adding the target's motion trajectory information, the direction of the target motion is given more weight, the other directions are given a smaller weight, and finally the target position is predicted by the density clustering method. The results show that the proposed algorithm effectively improves the accuracy of the target location prediction of the Siamese network when tracking targets.

In recent years, with the continuous development of artificial intelligence technology, biometric authentication based on computer vision technology have also been developed rapidly. In this paper, we propose a novel Shuffle dense networks (SDN) with combining ShuffleNet and DenseNet for biometric authentication. ShuffleNet is an extremely computation-efficient structure that can obtain more channels information. DenseNet makes full use of all hierarchical features, which can facilitate the flow of information. Specifically, dense skip connections is adopted for combining the low-level features and the high-level features to enhance the performance of the reconstruction and residual learning is applied for easing the difficulty of training the deep neural network. In addition, the grouped convolutions are introduced for reducing computational complexity and the number of parameters. What's more, the shuffle dense connections are proposed for mitigating the grouped convolutions problem of lacking information exchange between the groups. The proposed method is evaluated quantitatively and qualitatively on four benchmark datasets, and the experimental results of super-resolution illustrated that our SDN achieves great performance over the state-of-the-art frameworks.

In view of the long and narrow characteristics of the airport runway function area, this paper proposes a method combining the Haar -like feature and the spherical neural network to detect the airport runway in remote sensing images. The algorithm first uses Haar-like to extract the target features and trains the strong classifier, and then further uses a spherical neural network model to eliminate false alarms. The experimental results show that the algorithm achieves good accuracy in detecting airport runways.