Because the power grid system is easily damaged by external forces from construction vehicles, performing early warning of construction vehicles through object detection is of practical significance for protecting the safety of the power grid. However, accurate detection of engineering vehicles under complex and diverse scenarios is a challenging task. When the existing advanced anchor-free probabilistic two-stage detector CenterNet2 is directly applied to this task, the effect is unsatisfactory. The essential reason is that construction vehicles such as excavators, tower cranes, and truck cranes are different from ordinary objects. They usually have stretchable long robotic arms, resulting in serious deviation of the center point of the bounding box and excessive coverage of the background area by the detection bounding box. Therefore, this paper has made beneficial improvements to two-stage CenterNet2 model. Firstly, it proposes an adaptive positive sample selection algorithm based on Gaussian kernel function to improve the insufficient and unreasonable positive and negative sample sampling in the first-stage regional candidate network. Secondly, it furthers proposes a joint prediction of location accuracy and classification confidence with the IoU-aware category labels, which improves the bounding box ranking during the second-stage network and prevents some potential prediction results being mistakenly filtered out in the post-processing stage. The experimental results on our self-built engineering vehicle dataset indicate that the proposed method effectively alleviates the above problems and achieves promising results in actual engineering vehicle detection.

This paper proposes a novel neural network architecture dubbed Cross-Modal Integrative Feature Network (CMIFN) to address three challenges on sketch-based 3D shape retrieval. Firstly, existing methods, like those based on multi-view CNNs, mostly capture surface visual features, ignoring internal geometry features. CMIFN integrates both multi-view and geometry features of 3D objects, consequently extracting a comprehensive global feature. Secondly, existing methods often manipulate sketches to enhance them, which may introduce superfluous data. Utilising an attention mechanism, CMIFN keeps redundancy in check while achieving a more accurate sketch representation. Thirdly, existing methods often compare the distance between sketches and 3D shapes in the same feature space without considering their inherent differences, which can lead to sub-optimal retrieval results. CMIFN introduces a modality-weighted classifier module, which assigns different weights to features from different modalities, creating a shared feature space to minimize the gap between similar objects across modalities thus increase the retrieval accuracy. Our comprehensive experiments have demonstrated CMIFN’s state-of-the-art performance on benchmark datasets.

In this article, we propose the first geometry and texture (double) referenced interactive two-dimensional (2D) and 3D caricature generating and editing method. The main challenge of caricature generation lies in the fact that it not only exaggerates the facial geometry but also refreshes the facial texture. We address this challenge by utilizing the semantic segmentation maps as an intermediary domain, removing the influence of photo texture while preserving the person-specific geometry features. Specifically, our proposed method consists of two main components: 3D-CariNet and CariMaskGAN. 3D-CariNet uses sketches or caricatures to exaggerate the input photo into several types of 3D caricatures. To generate a CariMask, we geometrically exaggerate the photos using the projection of exaggerated 3D landmarks, after which CariMask is converted into a caricature by CariMaskGAN. In this step, users can edit and adjust the geometry of caricatures freely. Moreover, we propose a semantic detail preprocessing approach that considerably increases the details of generated caricatures and allows modification of hair strands, wrinkles, and beards. By rendering high-quality 2D caricatures as textures, we produce 3D caricatures with a variety of texture styles. Extensive experimental results have demonstrated that our method can produce higher-quality caricatures as well as support interactive modification with ease.

Existing GAN-based approaches to caricature generation mainly focus on exaggerating a character’s global facial structure. This often leads to the failure in highlighting significant facial features such as big eyes and hook nose. To address this limitation, we propose a new approach termed as G2L-CariGAN, which uses feature maps of spatial dimensions instead of latent codes for geometric exaggeration. G2L-CariGAN first exaggerates the global facial structure of the character on a low-dimensional feature map and then exaggerates its local facial features on a high-dimensional feature map. Moreover, we develop a caricature identity loss function based on feature maps, which well retains the character's identity after exaggeration. Our experiments have demonstrated that G2L-CariGAN outperforms the state-of-arts in terms of the quality of exaggerating a character and retaining its identity.

Recent studies have experimentally shown that we can achieve in non-Euclidean metric space effective and efficient graph embedding, which aims to obtain the vertices’ representations reflecting the graph’s structure in the metric space. Specifically, graph embedding in hyperbolic space has experimentally succeeded in embedding graphs with hierarchical-tree structure, e.g., data in natural languages, social networks, and knowledge bases. However, recent theoretical analyses have shown a much higher upper bound on non-Euclidean graph embedding’s generalization error than Euclidean one’s, where a high generalization error indicates that the incompleteness and noise in the data can significantly damage learning performance. It implies that the existing bound cannot guarantee the success of graph embedding in non-Euclidean metric space in a practical training data size, which can prevent non-Euclidean graph embedding’s application in real problems. This paper provides a novel upper bound of graph embedding’s generalization error by evaluating the local Rademacher complexity of the model as a function set of the distances of representation couples. Our bound clarifies that the performance of graph embedding in non-Euclidean metric space, including hyperbolic space, is better than the existing upper bounds suggest. Specifically, our new upper bound is polynomial in the metric space’s geometric radius $R$ and can be $O(\frac{1}{S})$ at the fastest, where $S$ is the training data size. Our bound is significantly tighter and faster than the existing one, which can be exponential to $R$ and $O(\frac{1}{\sqrt{S}})$ at the fastest. Specific calculations on example cases show that graph embedding in non-Euclidean metric space can outperform that in Euclidean space with much smaller training data than the existing bound has suggested.

Abstract Iris recognition is a popular research field in the biometrics, and it plays an important role in automatic recognition. Given sufficient training data, some deep learning‐based approaches have achieved good performance on iris recognition. However, when the training data are limited, overfitting may occur. To address this issue, in this paper, we proposed a few‐shot learning approach for iris recognition, based on model‐agnostic meta‐learning (MAML). To our best knowledge, we are the first to apply few‐shot learning for iris recognition. Our experiments on the benchmark datasets have demonstrated that the proposed approach can achieve higher performance than the original MAML, and it is competitive to deep learning‐based approaches.

In this paper, we present an approach for generating dialogues for characters within the context of computational narratives \nusing personality-based features for deep neural networks. The approach integrates the requirements of both narrative genres and personality traits for the definition of character-based stylistic models. \nThe modelling of characters’ features from existing datasets of complete stories permits the generation of personality-rich character dialogues. We present early results from an evaluation based on a sample of characters’ personality traits across different narrative genres, \ndemonstrating variability in the resulting dialogues

Facial Action Unit (AU) intensity prediction is essential to facial expression analysis and emotion recognition, and thus has attracted much attention from the community. In comparison, AU localization, albeit being important to emotion visualization and tracking, was relatively unexplored. In addition, as most existing AU intensity prediction methods take a cropped face image as input, their actual speed at run-time is often penalized by the pre-processing steps such as face detection and alignment. At the same time, their performance (in terms of inference speed), also does not scale well to multi-face images. To alleviate these problems, we propose a joint AU intensity prediction and localization method that works directly on the whole input image, thus eliminating the need of any pre-processing step and achieving the same inference speed regardless of the number of faces in the image. Based on the observation that different relevancy exists between AU intensities categories, a flexible cost function is proposed. At inference time, we introduce a non-maximum intensity suppression model to refine the prediction result. In order to leverage existing datasets without AU region groundtruth, we also propose an automatic AU region labeling method. Experiments on two benchmark databases, DISFA and FERA2015, show that the proposed approach outperforms the state-of-the-art methods on three metrics, ICC, MAE and F1 for the AU intensity prediction task.

Automatic animation synthesis has attracted much attention from the community. As most existing methods take a small number of discrete expressions rather than continuous expressions, their integrity and reality of the facial expressions is often compromised. In addition, the easy manipulation with simple inputs and unsupervised processing, although being important to the automatic facial expression animation applications, is relatively less concerned. To address these issues, we propose an unsupervised continuous automatic facial expression animation approach through action units (AU) transfer in the latent space of generative adversarial networks. The expression descriptor which is depicted with AU vector is transferred into the input image without the need of labeled pairs of images and even without their expressions and further network training. We also propose a new approach to quickly generate input image's latent code and cluster the boundaries of different AU attributes with their latent codes. Two latent code operators, vector addition and continuous interpolation, are leveraged for facial expression animation simulating align with the boundaries in the latent space. Experiments have shown that the proposed approach is effective on facial expression translation and animation synthesis.

Virtual reality (VR) in healthcare training has increased adoption and support, but efforts are still required to mitigate usability concerns. This study conducted a usability study of an in-use emergency medicine VR training application, available on commercially available VR hardware and with a standard interaction design. Nine users without prior VR experience but with relevant medical expertise completed two simulation scenarios for a total of 18 recorded sessions. They completed NASA Task Load Index and System Usability Scale questionnaires after each session, and their performance was recorded for the tracking of user errors. s Our results showed a medium (and potentially optimal) Workload and an above average System Usability Score. There was significant improvement in several factors between users' first and second sessions, notably increased Performance evaluation. User errors with the strongest correlation to usability were not directly tied to interaction design, however, but to a limited 'possibility space'. Suggestions for closing this 'gulf of execution' were presented, including 'voice control' and 'hand-tracking', which are only feasible for this commercial product now with the availability of the Oculus Quest headset. Moreover, wider implications for VR medical training were outlined, and potential next steps towards a standardized design identified.

Semi-supervised representation-based subspace clustering is to partition data into their underlying subspaces by finding effective data representations with partial supervisions. Essentially, an effective and accurate representation should be able to uncover and preserve the true data structure. Meanwhile, a reliable and easy-to-obtain supervision is desirable for practical learning. To meet these two objectives, in this paper we make the first attempt towards utilizing the orderly relationship, such as the data a is closer to b than to c, as a novel supervision. We propose an orderly subspace clustering approach with a novel regularization term. OSC enforces the learned representations to simultaneously capture the intrinsic subspace structure and reveal orderly structure that is faithful to true data relationship. Experimental results with several benchmarks have demonstrated that aside from more accurate clustering against state-of-the-arts, OSC interprets orderly data structure which is beyond what current approaches can offer.

Given ordinal relations such as the object $i$ is more similar to $j$ than $k$ is to $l$, ordinal embedding is to embed these objects into a low-dimensional space with all ordinal constraints preserved. Although existing approaches have preserved ordinal relations in Euclidean space, whether Euclidean space is compatible with true data structure is largely ignored, although it is essential to effective embedding. Since real data often exhibit hierarchical structure, it is hard for Euclidean space approaches to achieve effective embeddings in low dimensionality, which incurs high computational complexity or overfitting. In this paper we propose a novel hyperbolic ordinal embedding (HOE) method to embed objects in hyperbolic space. Due to the hierarchy-friendly property of hyperbolic space, HOE can effectively capture the hierarchy to achieve embeddings in an extremely low-dimensional space. We have not only theoretically proved the superiority of hyperbolic space and the limitations of Euclidean space for embedding hierarchical data, but also experimentally demonstrated that HOE significantly outperforms Euclidean-based methods.

Multiview representations reveal the latent information of the data from different perspectives, consistency and complementarity. Unlike most multiview learning approaches, which focus only one perspective, in this paper, we propose a novel unsupervised multiview learning algorithm, called comprehensive latent factor learning (CLFL), which jointly exploits both consistent and complementary information among multiple views. CLFL adopts a non-negative matrix factorization based formulation to learn the latent factors. It learns the weights of different views automatically which makes the representation more accurate. Experiment results on a synthetic and several real datasets demonstrate the effectiveness of our approach.

Existing methods on representation-based subspace clustering mainly treat all features of data as a whole to learn a single self-representation and get one clustering solution. Real data however are often complex and consist of multiple attributes or sub-features, such as a face image has expressions or genders. Each attribute is distinct and complementary on depicting the data. Failing to explore attributes and capture the complementary information among them may lead to an inaccurate representation. Moreover, a single clustering solution is rather limited to depict data, which can often be interpreted from different aspects and grouped into multiple clusters according to attributes. Therefore, we propose an innovative model called attributed subspace clustering (ASC). It simultaneously learns multiple self-representations on latent representations derived from original data. By utilizing Hilbert Schmidt Independence Criterion as a co-regularizing term, ASC enforces that each self-representation is independent and corresponds to a specific attribute. A more comprehensive self-representation is then established by adding these self-representations. Experiments on several benchmark image datasets have demonstrated the effectiveness of ASC not only in terms of clustering accuracy achieved by the integrated representation, but also the diverse interpretation of data, which is beyond what current approaches can offer.

In this paper, we develop a new approach to blending of constant and varying parametric surfaces with curvature continuity. We propose a new mathematical model consisting of a vector-valued sixth-order partial differential equation (PDE) and time-dependent blending boundary constraints, and develop an approximate analytical solution of the mathematical model. The good accuracy and high computational efficiency are demonstrated by comparing the new approximate analytical solution with the corresponding accurate closed form solution. We also investigate the influence of the second partial derivatives on the continuity at trimlines, and apply the new approximate analytical solution in blending of constant and varying parametric surfaces with curvature continuity.

Nonnegative matrix factorization (NMF), a well-known technique to find parts-based representations of nonnegative data, has been widely studied. In reality, ordinal relations often exist among data, such as data i is more related to j than to q. Such relative order is naturally available, and more importantly, it truly reflects the latent data structure. Preserving the ordinal relations enables us to find structured representations of data that are faithful to the relative order, so that the learned representations become more discriminative. However, current NMFs pay no attention to this. In this paper, we make the first attempt towards incorporating the ordinal relations and propose a novel ranking preserving nonnegative matrix factorization (RPNMF) approach, which enforces the learned representations to be ranked according to the relations. We derive iterative updating rules to solve RPNMF's objective function with convergence guaranteed. Experimental results with several datasets for clustering and classification have demonstrated that RPNMF achieves greater performance against the state-of-the-arts, not only in terms of accuracy, but also interpretation of orderly data structure.

Non-negative matrix factorization (NMF), a method for finding parts-based representation of non-negative data, has shown remarkable competitiveness in data analysis. Given that real-world datasets are often comprised of multiple features or views which describe data from various perspectives, it is important to exploit diversity from multiple views for comprehensive and accurate data representations. Moreover, real-world datasets often come with high-dimensional features, which demands the efficiency of low-dimensional representation learning approaches. To address these needs, we propose a diverse NMF (DiNMF) approach. It enhances the diversity, reduces the redundancy among multiview representations with a novel defined diversity term and enables the learning process in linear execution time. We further propose a locality preserved DiNMF (LP-DiNMF) for more accurate learning, which ensures diversity from multiple views while preserving the local geometry structure of data in each view. Efficient iterative updating algorithms are derived for both DiNMF and LP-DiNMF, along with proofs of convergence. Experiments on synthetic and real-world datasets have demonstrated the efficiency and accuracy of the proposed methods against the state-of-the-art approaches, proving the advantages of incorporating the proposed diversity term into NMF.

Real data are usually complex and contain various components. For example, face images have expressions and genders. Each component mainly reflects one aspect of data and provides information others do not have. Therefore, exploring the semantic information of multiple components as well as the diversity among them is of great benefit to understand data comprehensively and in-depth. However, this cannot be achieved by current nonnegative matrix factorization (NMF)-based methods, despite that NMF has shown remarkable competitiveness in learning parts-based representation of data. To overcome this limitation, we propose a novel multi-component nonnegative matrix factorization (MCNMF). Instead of seeking for only one representation of data, MCNMF learns multiple representations simultaneously, with the help of the Hilbert Schmidt Independence Criterion (HSIC) as a diversity term. HSIC explores the diverse information among the representations, where each representation corresponds to a component. By integrating the multiple representations, a more comprehensive representation is then established. A new iterative updating optimization scheme is derived to solve the objective function of MCNMF, along with its correctness and convergence guarantees. Extensive experimental results on real-world datasets have shown that MCNMF not only achieves more accurate performance over the state-of-the-arts using the aggregated representation, but also interprets data from different aspects with the multiple representations, which is beyond what current NMFs can offer.

Nonnegative matrix factorization (NMF) as a popular technique to find parts-based representations of nonnegative data has been widely used in real-world applications. Often the data which these applications process, such as motion sequences and video clips, are with ordered structure, i.e., consecutive neighbouring data samples are very likely share similar features unless a sudden change occurs. Therefore, traditional NMF assumes the data samples and features to be independently distributed, making it not proper for the analysis of such data. In this paper, we propose an ordered robust NMF (ORNMF) by capturing the embedded ordered structure to improve the accuracy of data representation. With a novel neighbour penalty term, ORNMF enforces the similarity of neighbouring data. ORNMF also adopts the L2,1-norm based loss function to improve its robustness against noises and outliers. A new iterative updating optimization algorithm is derived to solve ORNMF's objective function. The proofs of the convergence and correctness of the scheme are also presented. Experiments on both synthetic and real-world datasets have demonstrated the effectiveness of ORNMF.

We propose a novel multi-view document clustering method with the graph-regularized concept factorization (MVCF). MVCF makes full use of multi-view features for more comprehensive understanding of the data and learns weights for each view adaptively. It also preserves the local geometrical structure of the manifolds for multi-view clustering. We have derived an efficient optimization algorithm to solve the objective function of MVCF and proven its convergence by utilizing the auxiliary function method. Experiments carried out on three benchmark datasets have demonstrated the effectiveness of MVCF in comparison to several state-of-the-art approaches in terms of accuracy, normalized mutual information and purity.

Subspace clustering aims to partition the data points drawn from a union of subspaces according to their underlying subspaces. For accurate semisupervised subspace clustering, all data that have a must-link constraint or the same label should be grouped into the same underlying subspace. However, this is not guaranteed in existing approaches. Moreover, these approaches require additional parameters for incorporating supervision information. In this paper, we propose a constrained low-rank representation (CLRR) for robust semisupervised subspace clustering, based on a novel constraint matrix constructed in this paper. While seeking the low-rank representation of data, CLRR explicitly incorporates supervision information as hard constraints for enhancing the discriminating power of optimal representation. This strategy can be further extended to other state-of-the-art methods, such as sparse subspace clustering. We theoretically prove that the optimal representation matrix has both a block-diagonal structure with clean data and a semisupervised grouping effect with noisy data. We have also developed an efficient optimization algorithm based on alternating the direction method of multipliers for CLRR. Our experimental results have demonstrated that CLRR outperforms existing methods.

The regular physical activity with enough amounts of intensity, duration and frequency plays a key role in our health and body shape. However, for sedentary individuals who have negative or even painful feeling on exercise, it is a challenge to maintain enough activities. We propose a pleasurable persuasive model (PPM) to tackle the challenge. PPM emphasizes the combination of psychological driven and physiological adaptation, encouraging health behavior change in an aesthetical pleasurable way. Coming with a complete set of design strategies including pleasure, guidance, motivation, and reminder, a prototype system is developed to experiment the effectiveness and feasibility of the approach. The real time biofeedback and aesthetical pleasure is integrated seamlessly into this system. Results from a three-week in-lab user study have demonstrated that, the system is able to encourage regular physical activities with enough amounts of intensity, duration and frequency in a pleasurable way, proving the effectiveness of PPM.

Smart phones have become the hub of people lives due to the overwhelming number and extensive range of apps available in app stores that are available to support their daily tasks. On average, smart phone users have around 100 apps installed on their devices and the number is ever growing. Thus, it becomes crucial to make sure they can quickly access these apps. In this paper, we present an exploratory study to understand users' memorability of their self-defined gestures for 15 frequently used mobile apps. The results show that although participants recalled their self-defined gestures most of the time, there are still certain factors that can influence their recall. The paper further analyses the underlining reasons and discusses how such issues could be addressed from a technical perspective.

Nonnegative matrix factorization (NMF), which aims at finding parts-based representations of nonnegative data, has been widely applied to a range of applications such as data clustering, pattern recognition and computer vision. Real-world data are often sparse and noisy which may reduce the accuracy of representations. And a small portion of data may have prior label information, which, if utilized, can improve the discriminability of representations. In this paper, we propose a robust semi-supervised nonnegative matrix factorization (RSSN-MF) approach which takes all factors above into consideration. RSSNMF incorporates the label information as an additional constraint to guarantee that the data with the same label have the same representation. It addresses the sparsity of data and accommodates noises and outliers consistently via L2,1-norm. An iterative updating optimization scheme is derived to solve RSSNMF's objective function. We have proven the convergence of this optimization scheme by utilizing auxiliary function method and the correctness based on the Karush-Kohn-Tucker condition of optimization theory. Experiments carried on well-known data sets demonstrate the effectiveness of RSSNMF in comparison to other existing state-of-the-art approaches in terms of accuracy and normalized mutual information.

ABSTRACT In this publication we will look at the different methods presented over the past few decades which attempt to recreate digital paintings. While previous surveys concentrate on the broader subject of non‐photorealistic rendering, the focus of this paper is firmly placed on painterly rendering techniques. We compare different methods used to produce different output painting styles such as abstract, colour pencil, watercolour, oriental, oil and pastel. Whereas some methods demand a high level of interaction using a skilled artist, others require simple parameters provided by a user with little or no artistic experience. Many methods attempt to provide more automation with the use of varying forms of reference data. This reference data can range from still photographs, video, 3D polygonal meshes or even 3D point clouds. The techniques presented here endeavour to provide tools and styles that are not traditionally available to an artist. Copyright © 2012 John Wiley & Sons, Ltd.

ABSTRACT The use of linear interpolation to blend different terrain types with distinct features produces translucency artefacts that can detract from the realism of the scene. The approach presented in this paper addresses the feature agnosticism of linear blending and makes the distinction between features (bricks, cobble stone, etc.) and non‐features (cement, mortar, etc.). Using the blend weights from Bloom's texture splatting, intermittent texture transitions are generated on the fly without the need for artistic intervention. Furthermore, feature shapes are modified dynamically to give the illusion of wear and tear, thus further reducing repetition and adding authenticity to the scene. The memory footprint is constant regardless of texture complexity and uses nearly eight times less texture memory when compared to tile‐based texture mapping. The scalability and diversity of our approach can be tailored to a wide range of hardware and can utilize textures of any size and shape compared to the grid layout and memory limitations of tile‐based texture mapping. Copyright © 2012 John Wiley & Sons, Ltd.

Abstract In this paper, we propose an instant shadow generation technique for 2D animation, especially Japanese Anime. In traditional 2D Anime production, the entire animation including shadows is drawn by hand so that it takes long time to complete. Shadows play an important role in the creation of symbolic visual effects. However shadows are not always drawn due to time constraints and lack of animators especially when the production schedule is tight. To solve this problem, we develop an easy shadowing approach that enables animators to easily create a layer of shadow and its animation based on the character's shapes. Our approach is both instant and intuitive. The only inputs required are character or object shapes in input animation sequence with alpha value generally used in the Anime production pipeline. First, shadows are automatically rendered on a virtual plane by using a Shadow Map1based on these inputs. Then the rendered shadows can be edited by simple operations and simplified by the Gaussian Filter. Several special effects such as blurring can be applied to the rendered shadow at the same time. Compared to existing approaches, ours is more efficient and effective to handle automatic shadowing in real‐time. Copyright © 2009 John Wiley & Sons, Ltd.

Animation created using computer graphics is seen through a viewport which is dictated by what the director or producer wants the consumer to watch. This includes the usual cinematography to bring out the best dramatical effects. Consumers, however, do not have a choice but to passively receive the imagery that unfolds through the screen. This paper proposes the concept of a consumer editable animation, which aims to provide consumers with the flexibility to change attributes of the scene and also to decide what and how they want to view the final animation. Another key point is that all data are vector-based and the animation sequences are therefore rescalable.

Skinning existing animation frames or examples is exploited actively to find the most suitable scheme that is capable of capturing deformations from given mesh sequences. It is necessary to approximate joint transformations by a fitting algorithm that usually involves solving a large scale linear system. In this paper, we reduce the dimensions of the linear system substantially by representing example meshes as progressive decimated models. These models are reconstructed from augmented deformation sensitive decimation (ADSD) that is able to handle large deformations while maintaining connectivity relationship throughout all example meshes. We also show that skinning can be propagated to decimated models, which allows animations to be scalable to specific applications with varied requirements of qualities.

This paper proposes a bidirectional modeling approach. It aims to assist online collaboration on 2D to 3D modeling. Two "worlds" of modeling are proposed in our pipeline. A free-form 3D model can be generated in the "creation world" (CW). Then models are transferred to another "world", the "viewing world" (VW), and integrated with existing virtual scene. Models in the "viewing world" can also be transferred back to the "creation world" for further refinement. All operations performed in the "creation world" are based on our sketch-up technique, which is a new method to accomplish 2D to 3D reconstruction. In this method, 3D models are created through a traditional and intuitive way, "painting", with a mouse/stylus. The approach proposed in this paper can be applied to help online e-edutainment and e-learning applications. It is expected to help multi-user modeling and geometric learning online. With our method, collaborative modeling on the Web can be carried out in an easy and intuitive manner.

Conveying shape using feature lines is an important visualization tool in visual computing. The existing feature lines (e.g., ridges, valleys, silhouettes, suggestive contours, etc.) are solely determined by local geometry properties (e.g., normals and curvatures) as well as the view position. This paper is strongly inspired by the observation in human vision and perception that a sudden change in the luminance plays a critical role to faithfully represent and recover the 3D information. In particular, we adopt the edge detection techniques in image processing for 3D shape visualization and present Photic Extremum Lines (PELs) which emphasize significant variations of illumination over 3D surfaces. Comparing with the existing feature lines, PELs are more flexible and offer users more freedom to achieve desirable visualization effects. In addition, the user can easily control the shape visualization by changing the light position, the number of light sources, and choosing various light models. We compare PELs with the existing approaches and demonstrate that PEL is a flexible and effective tool to illustrate 3D surface and volume for visual computing.

Abstract Disk B‐spline curve (DBSC) is previously proposed for drawing and animation. To generate inbetweens, linear interpolation is applied between points evenly taken in parametric domain of two DBSCs without incorporating characteristics of shape or motion, which results in distortion and unrealistic motion in animation. In this paper, more information in keyframes is extracted and utilized in inbetween generation. Points with high curvature are computed and corresponded between strokes in interpolation, which preserves features of strokes in animation. In addition, global motion of a character or its various components is estimated and interpolated as well, which retains the shapes during the motion. By applying the information to interpolation, the distortion is eliminated and smoother sequence of animation is achieved. Copyright © 2006 John Wiley & Sons, Ltd.

Abstract This paper proposes a Hierarchical Region Matching (HRM) approach for computer‐assisted auto coloring. The region‐level analysis in traditional 2D animation is expanded into several component levels with a novel hierarchization method. With the hierarchy, various region matching algorithms can be applied from the first/highest to the last/lowest component level. HRM improves the matching accuracy and may deal with matching errors caused by occlusion, thus making the matching more robust, as verified by the results. Copyright © 2005 John Wiley & Sons, Ltd.

Automatic inbetweening is one of the main focuses in computer assisted cel animation as inbetweening process is traditionally time-consuming and labor-intensive in the production of cartoon animation. Most previous work demand either lots of modeling or working with complicated programs and their interfaces, which do not take much animator's expertise into consideration, as animators are usually more capable of drawing pictures on the paper than programming with computer. An approach proposed in this paper aims to provide an easy-to-use system which automatically models key frames "on the fly " and interpolates them in several layers, including object size and position, line curvatures and curve texture in order to preserve artistic style of the hand-drawn key frames and make the motion smooth and natural. Without much user interaction and complicated program interface the system may be tuned, uploaded into the Web so that not only professional artists but those who are interested in cartoon but don't have much time or skill on drawing frames or inexperienced at using computer, like students, free-lance animators, etc. may benefit from using the system, for example, creating animation clips for the Web. The results show that the algorithm works well although it leaves areas for further research to extend and improve the algorithm to work with as many different types of key frames as possible.

Computer-assisted auto coloring (CAAC) has great potential in terms of lowering production cost and saving time in cel animation production. In this paper, a novel approach to automatically color the animation character of line drawings based on region matching and master frames is proposed. Firstly, some important attributes of a region such as curve length, character points, area etc. are investigated. Then, based on these attributes, a detailed process of region matching is presented followed by the coloring process. The results show that our approach can straightforwardly handle most cases, hence the aim of saving time and labor is realized.