3-Dscanning has various applications in industrial design. However, the noisy point clouds being generated are difficult to be used in the applications directly. The ease of editing and lightweight nature of wireframes make it highly suitable for industrial design. To address this issue, WG-Net is proposed for generating wireframes from noisy point clouds. An edge primitive detection network that includes a multilevel feature extraction module and a feature fusion module is designed for point classification, primitive segmentation, and displacement vector prediction. Based on the classification and segmentation results of edge points, targeted fitting methods are applied to accurately fit each category of edge primitives, ensuring precise geometric representation. Finally, fitting results are integrated into a complete wireframe structure. Through extensive experiments on computer-aided design datasets, WG-Net achieved significant performance improvements compared to state-of-the-art methods. In addition, we have verified the feasibility and practical applicability of WG-Net on real scanned data.

Recently, Mamba has gained widespread attention due to its ability to model long-range dependencies with linear computational complexity. To explore the application of Mamba in 2D human pose estimation, we propose MatPose, a Mamba-Transformer hybrid model specifically designed for efficient 2D human pose estimation. The model aims to combine Mamba’s efficient modeling of long-range dependencies with the powerful global context modeling capabilities of the Transformer to effectively extract human pose keypoints. Initially, to address the lack of local features when Mamba is applied to computer vision tasks, we design a Cross-Stage Multi-Scale Convolution (CSMSC) module by integrating multi-scale convolution, cross-stage feature fusion, and spatial attention mechanisms to effectively extract local features. Then, to mitigate the long-range forgetting issue inherent in Mamba, we shorten the sequence length using the Conv-Reduce operation. In addition, we design a Channel Selection Attention (CSA) mechanism to compensate for the feature loss caused by the Conv-Reduce operation. Finally, to explore a suitable integration method for the Mamba-Transformer hybrid model in 2D human pose estimation, we conduct a comprehensive ablation study on the feasibility of integrating Mamba and Transformer models. Experimental results show that the proposed method, compared to the baseline model, improves performance while reducing computational overhead. On the COCO val2017 dataset, MatPose achieves an AP of 74.6 with only 5.18 GFLOPs, outperforming most existing human pose estimation models.

Reconstruction of 3D roof from airborne LiDAR point clouds is an important task in the field of remote sensing and photogrammetry. Due to the high noise, large volume, and structural complexity inherent in LiDAR point clouds, traditional point cloud processing methods have limited performance in terms of accuracy and robustness. Most existing methods rely on corner point detection and edge prediction to extract and reconstruct roof structures. However, corner points are often sparsely distributed and difficult to locate precisely, resulting in noticeable geometric deviations and incomplete structural reconstruction. Therefore, generating high-quality 3D roof from complex LiDAR point clouds is still a challenging problem to be solved. To address these issues, we propose a novel roof reconstruction method RR-Net that combines edge segmentation and wireframe generation. Firstly, an innovative unified point cloud edge segmentation network was developed, achieving integrated edge detection, segmentation, and denoising. Secondly, based on the segmentation results from this network, an efficient and robust pipeline for wireframe generation and roof reconstruction was designed, enabling automated transformation from airborne LiDAR point clouds to roof models. Extensive experiments on the Building dataset demonstrate that RR-Net can efficiently and accurately reconstruct roofs from airborne LiDAR point clouds. RR-Net achieves 95.7% accuracy in edge detection and reduces the chamfer distance (CD) error of the wireframe to 0.021. The results of RR-Net are publicly available at: https://yecoxu.github.io/publications/RR-Net/.

Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of success. However, few methods exist for generating full-body animations, and the portability of virtual character gestures and facial animations has not received sufficient attention. Therefore, we propose a deep-learning-based audio-to-animation-and-blendshape (Audio2AB) network that generates gesture animations andARK it’s 52 facial expression parameter blendshape weights based on audio, audio-corresponding text, emotion labels, and semantic relevance labels to generate parametric data for full- body animations. This parameterization method can be used to drive full-body animations of virtual characters and improve their portability. In the experiment, we first downsampled the gesture and facial data to achieve the same temporal resolution for the input, output, and facial data. The Audio2AB network then encoded the audio, audio- corresponding text, emotion labels, and semantic relevance labels, and then fused the text, emotion labels, and semantic relevance labels into the audio to obtain better audio features. Finally, we established links between the body, gestures, and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss function. By using audio, audio-corresponding text, and emotional and semantic relevance labels as input, the trained Audio2AB network could generate gesture animation data containing blendshape weights. Therefore, different 3D virtual character animations could be created through parameterization. The experimental results showed that the proposed method could generate significant gestures and facial animations.

Although the cartoon industry has developed rapidly in recent years, few studies pay special attention to cartoon image quality assessment (IQA). Unfortunately, applying blind natural IQA algorithms directly to cartoons often leads to inconsistent results with subjective visual perception. Hence, this brief proposes a blind cartoon IQA method based on convolutional neural networks (CNNs). Note that training a robust CNN depends on manually labeled training sets. However, for a large number of cartoon images, it is very time-consuming and costly to manually generate enough mean opinion scores (MOSs). Therefore, this brief first proposes a full reference (FR) cartoon IQA metric based on cartoon-texture decomposition and then uses the estimated FR index to guide the no-reference IQA network. Moreover, in order to improve the robustness of the proposed network, a large-scale dataset is established in the training stage, and a stochastic degradation strategy is presented, which randomly implements different degradations with random parameters. Experimental results on both synthetic and real-world cartoon image datasets demonstrate the effectiveness and robustness of the proposed method.

Most of the existing human pose estimation methods improve accuracy by constantly increasing computational resources. However, balancing the efficiency and efficacy of the model is the key to enhancing the real application value. In this work, we present a Fast and Effective Transformer model to ensure the efficiency and efficacy of the model, called FET. Specifically, the FET consists of three parts: Feature Extraction Module (FEM), Feature Interaction Module (FIM) and Feature Decode Module (FDM). The FEM is used to efficiently extract low-level features from input images. Unlike CNN-based strategies, the FIM enables our model to capture global dependencies by self-attention, thus improving the accuracy for human pose estimation. The FDM is a multistage way that gradually recovers the size of the features to obtain a higher-quality target heatmap. In addition, Feature Squeeze Attention is introduced in the FET to further improve the overall performance of our model. Extensive experiments show that our method is 1.7× and 7× faster than SimpleBaseline and HRNet-32, respectively, while achieving comparable or even better results with the most state-of-the-art methods on the COCO dataset and the MPII dataset.

Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in real-world early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos. At the same time, the method also won the first place in the MSU Deinterlacer Benchmark. The code is available at: https://github.com/anymyb/MFDIN.

With the development of display technology, bit-depth expansion (BDE) has emerged as a basic process to display low-bit-depth image and video resources on high-bit-depth monitors. Most current BDE methods are based on traditional algorithms, and the few existing methods based on deep neural networks still suffer from loss of pixel-level details or from high computational cost. This paper proposes a lightweight but efficient BDE network that can effectively improve the capacity of shallow network by introducing a residual-block-in-residual-block structure. Furthermore, the proposed network adopts residual network architecture and dilated convolution to balance the preservation of pixel-level information and the expansion of the receptive field. Hence, the proposed method can also totally remove significant artifacts from very low-bit-depth images. Experimental results demonstrate that the proposed method can achieve performance comparable to or even better than that of some state-of-the-art methods while having much lighter architecture and fewer parameters.

With the remarkable development of sensor devices and the Internet of Things (IoT), today's researchers can easily know what changes have taken place in the real world by acquiring a 3-D model. Conversely, a large amount of image data promotes the development of perceptual computing technology. In this article, we focus on modeling 3-D scenes from the multisource image data obtained from the IoT with cameras. Although great progress has been made in 3-D reconstruction, it is still challenging to recover the 3-D model from IoT data because the captured images are usually noisy, incomplete, varying scale, and with repetitive structures or features. In this article, we propose an accurate 3-D reconstruction method under IoT environments for perceptual computing of the scene. This method consists of sparse, dense, and surface reconstruction processes, which can gradually recover high-quality geometric models from the image data and efficiently deal with various repetitive structures. By analyzing the reconstructed model, we can detect the changes of scenes. We evaluate the proposed method on the benchmark data sets (i.e., tanks and temples) and publicly available data sets(in which samples usually contain repeated structures, lighting change, and different scales). Experimental results show that the proposed method outperforms the state-of-the-art methods according to the standard evaluation metric. We also use our method to enhance the real scenes with virtual objects, thus producing promising results.

Benefits from artificial intelligence and the Internet of Vehicles (IoV), Management of modern transportation have great progress, especially in urban areas. However, traditional traffic video analysis and visualization are usually conducted in offsite and textural environments, i.e., text and number, which do not promote user's sensorial perception and interaction. Thus, the problem that how to use modern novel techniques to analyze traffic video for improving intelligent transportation is so emergency. In this paper, we introduce a joint 3D reconstruction and object tracking approach to traffic video analysis under the IoV environment, which is an integrative framework and consists of 3D reconstruction, object detection, and visual tracking. The 3D reconstruction system is connected to the Internet of Vehicles and integrated into the system to retrieve image data for recovering the 3D model of vehicles, and then, visualizing vehicle trajectories in real-time by augmented reality. And the system can also locate the vehicle's position in real-time. The experiments in both laboratory and practice show great feedback, which will effectively contribute to intelligent transportation.

Current blind image quality assessment (BIQA) algorithms are mainly designed for natural images. Unfortunately, cartoon and cartoon-like images are quite different from natural images. Hence, recent BIQA methods are not very robust to cartoon images. In this paper, we propose a specific BIQA algorithm designed for cartoon images, which consists of the following terms. First, a cartoon image is divided into edge areas and nonedge areas via a Tchebichef moment (TM)-based process. Second, a multiorder sharpness statistic term is used to measure the quality of the edges, and a sharpness statistic prior model of high-quality (HQ) cartoon images is built. Finally, a local encoding statistic term is adopted to describe the textural complexity in the nonedge areas, and a texture statistic prior model is also established. The experimental results on the cartoon image datasets demonstrate that the proposed method can accurately evaluate the visual quality of cartoon images and is more suitable for cartoon scenarios than some traditional BIQA algorithms.

Bit-depth expansion (BDE) is important for displaying a low bit-depth image in a high bit-depth monitor. Current BDE algorithms often utilize traditional methods to fill the missing least significant bits and suffer from multiple kinds of perceivable artifacts. In this paper, we present a deep residual network-based method for BDE. Based on the different properties of flat and non-flat areas, two channels are proposed to reconstruct these two kinds of areas, respectively. Moreover, a simple yet efficient local adaptive adjustment preprocessing is presented in the flat-area-channel. By combining the benefits of both the traditional debanding strategy and network-based reconstruction, the proposed method can further promote the subjective quality of the flat area. Experimental results on several image sets demonstrate that the proposed BDE network can obtain favorable visual quality as well as decent quantitative performance.

With the ascension of computer processing capacity, the problems of massive satellite images presentation encountered in the rendering frame rate, large data scheduling, external memory organization has been basically solved, Google earth put forward one multi-user solution dependent on the powerful cluster rendering technology and collaborative network transmission technology. However, in the limited resources of the stand-alone system, the display of multi-user collaborative data become another challenge. This paper proposed a collaborative scheduling scheme for multi-user scheduling problem of satellite image data in the stand-alone mode, in the fully enhance the system resource utilization condition, balanced user's average experience and data throughput condition. Finally, in the prototype system, we verify its validity and analyze its efficiency and interactivity though the user's experience way.

An animation character, which has several duplications in one virtual scene, is usually represented just by a same 3D model. It results in monotonous and boring scenes. A micro-deformation method which can create an interesting scene include many 3D models of different shape from the same character is proposed in this paper. By geometric approximation the real-time algorithm of micro-deformation which uses elementary geometry and sweep geometry as the deformation reference objects is studied. The experiments on 3D game character demonstrate that the algorithm is real-time and effective. So it can be used in virtual scene to get an abundant and interesting scene.

A novel method for three-dimensional (3D) residential building reconstruction in urban areas using LiDAR (light detection and ranging) data is proposed. The main contribution of this work is the automatic segmentation of roof points and roof type recognition and reconstruction based on sparse LiDAR data. Using minimum bounding rectangle (MBR) method and model-based reconstruction, we are able to automatically identify individual buildings from cluttered residential areas and re-create building models with improved accuracy in a reasonably short time. We applied our method to urban sites in the city of New Orleans and demonstrated that the method identified building measurements successfully from LiDAR data and rebuilt 3D models effectively. Our experiments show that even in the presence of noise we can successfully reconstruct small buildings given relatively sparse LiDAR samples with help from template databases.

Maximal clearance is an important property that is highly desirable in multi-agent motion planning. However, it is also inherently difficult to attain. We propose a novel approach to achieve maximal clearance by exploiting the ability of evenly distributing a set of points by a centroidal Voronoi tessellation (CVT). We adapt the CVT framework to multi agent motion planning by adding an extra time dimension and optimize the trajectories of the agents in the augmented domain. As an optimization framework, our method can work naturally on complex regions. We demonstrate the effectiveness of our algorithm in achieving maximal clearance in motion planning with some examples.

Animation design is a complicated group project which usually has a long lifecycle, involves huge participants and has diversified media data. In this paper, the idea of collaborative design is brought into the process of animation design, for finding the difficulties and low efficient sectors caused by the lack of collaboration during the whole design process, with the purpose of questing for appropriate solutions to collaboration. Related technologies of collaborative application to four aspects, including pre-creation, task allocation, data management and collaborative perception, are discussed, in order to improve efficiency, and enhance communications and data sharing to some extent. Finally, two instances about collaborative innovation of character relationship in scripts and animation scene design with collaborative template are given, so the perspective that animation design will be a new domain for researches and applications of collaboration is indicated.

In the basis of photon texture data generated by parallelized algorithm, we propose the real-time rendering algorithm. This method stores pre-computed results of photon mapping as textures before rendering, and looks for adjacent photons by programming on GPU (graphics processing unit). The algorithm takes full advantage of the computing capacity of GPU to accelerate the process of searching photon map. The experiment has proved that this algorithm can enhance efficiency of rendering for real-time interaction, also ensure rendering effect.

Constraints conflict occurs inevitably in collaborative design process. Therefore, conflict detection and resolution becomes critical for successfully completing the design. This paper puts forward a novel process of constraints conflict visualization to help designers to solve the problem. The process begins with modeling of constraint information based on constraints satisfaction problem (CSP), then presents an effective algorithm to detect conflicts, finally the visualization of constraints result is displayed to designers for pointing out the direction of conflict resolution or personalized improvement. At last, an application of V belt drive design is described, which demonstrates the reasonableness and feasibility of the proposed technique.

Task partition is a critical problem of collaborative conceptual design. Aiming at the shortage that current task partition methods don't accord to innovative functional reasoning that is the kernel process and essence embodiment of conceptual design, a new task partition method for function tree according to innovative functional reasoning is proposed. To begin with, the concept of task module is proposed as the basic unit of task pre-partition before task module pre-partition algorithm that generates initial task modules is put forward. Furthermore, based on analyzing and gaining three basic constraint relationships: including, independent and innovative conflict relationship, M- TPG (module-driven task precedence graph) generated from the former two relationships is introduced into this field as the basic tool of task management. Lastly, task partition algorithm based on M-TPG with three basic principles for innovation is given. The new method is derived from clustering of microcosmic elements of innovative functional reasoning and conflicted task modules, which can obtain deeper cohesiveness and more reasonable results.

Reasonable task planning is the key technique to improve cooperation quality and the design efficiency in collaborative design. This paper proposes the concept of Task Precedence Graph (TPG) as the basis of visual task-driven for cooperative task design and task communication. Some constraint transformation rules have been abstracted through the analysis of constraint information, followed which the transformation algorithm based on coupling has been put forward for generation of TPG as well. The collaborative design flow is driven by the visual form of TPG, emphasizing the influence of collaborative design environment on designers. The visual task-driven mode has been verified by a collaborative design system that is applied in domains like Die design and Sofa design, confirming the effectiveness of the mode on task planning and design organization.

Constraint information is crucial content of CSCD. It becomes more complicated and various with the expanding application and hard to manage. In order to control collaborative design flow efficiently, detect constraint conflicts early and decrease contradiction extension speed, intuitive and vivid constraint information visualization method is created. This paper discusses detailed signification and formalized description of constraint information visualization in CSCD based on classification and representations, puts forward two key procedures in visualization: one is counterpart modes between constraint information and available visualization techniques. The other one is harmony system of assessment based on constraint harmony concept. Crucial steps of constraint information visualization in CSCD such as constraint information mapping, dynamic track have been pointed out as well. The application of constraint information in collaborative design will give an important direction to complicated system control and complicated constraints management

Template technology has a great contribution to domain of design, especially computer aided design. Based on existing technologies and methodology, authors have applied the concept of cooperative template to the study of visual design environment. A framework of visual design environment of cooperative template is introduced including cooperative template description, element constraint, working flow and parallel mechanism. Several instances like Die cooperative & Sofa are provided to demonstrate the features and utility of the design environment. As a new concept, result of application makes authors believe that cooperative template play an important role in information-reducing, relation-order and design efficiency in CSCD environment.

R&D of fusion energy is becoming more and more important in the world. Up to now, tokamak is a typical fusion experiment device using magnetic confinement. Although the recent experiments and associated theoretical studies of fusion energy development have proven the feasibility of fusion power, it's commonly realized that it needs hard work before fusion energy could be commercially and economically utilized. It means that there will many new concepts and schemes to be supported and to be optimized. The paper studies stages of conceptual design and introduces a method of cooperative template. A novel idea and methodology of computer aided conceptual design is proposed according to characteristics of function, behavior and structures in tokamak.