The psc-CVM assessment system: A three-stage type system for CVM assessment based on deep learning.

BACKGROUND: Many scholars have proven cervical vertebral maturation (CVM) method can predict the growth and development and assist in choosing the best time for treatment. However, assessing CVM is a complex process. The experience and seniority of the clinicians have an enormous impact on judgment. This study aims to establish a fully automated, high-accuracy CVM assessment system called the psc-CVM assessment system, based on deep learning, to provide valuable reference information for the growth period determination. METHODS: This study used 10,200 lateral cephalograms as the data set (7111 in train set, 1544 in validation set and 1545 in test set) to train the system. The psc-CVM assessment system is designed as three parts with different roles, each operating in a specific order. 1) Position Network for locating the position of cervical vertebrae; 2) Shape Recognition Network for recognizing and extracting the shapes of cervical vertebrae; and 3) CVM Assessment Network for assessing CVM according to the shapes of cervical vertebrae. Statistical analysis was conducted to detect the performance of the system and the agreement of CVM assessment between the system and the expert panel. Heat maps were analyzed to understand better what the system had learned. The area of the third (C3), fourth (C4) cervical vertebrae and the lower edge of second (C2) cervical vertebrae were activated when the system was assessing the images. RESULTS: The system has achieved good performance for CVM assessment with an average AUC (the area under the curve) of 0.94 and total accuracy of 70.42%, as evaluated on the test set. The Cohen's Kappa between the system and the expert panel is 0.645. The weighted Kappa between the system and the expert panel is 0.844. The overall ICC between the psc-CVM assessment system and the expert panel was 0.946. The F1 score rank for the psc-CVM assessment system was: CVS (cervical vertebral maturation stage) 6 > CVS1 > CVS4 > CVS5 > CVS3 > CVS2. CONCLUSIONS: The results showed that the psc-CVM assessment system achieved high accuracy in CVM assessment. The system in this study was significantly consistent with expert panels in CVM assessment, indicating that the system can be used as an efficient, accurate, and stable diagnostic aid to provide a clinical aid for determining growth and developmental stages by CVM.

HairStyle Editing via Parametric Controllable Strokes.

In this work, we propose a stroke-based hairstyle editing network, dubbed HairstyleNet, allowing users to conveniently change the hairstyles of an image in an interactive fashion. Different from previous works, we simplify the hairstyle editing process where users can manipulate local or entire hairstyles by adjusting the parameterized hair regions. Our HairstyleNet consists of two stages: a stroke parameterization stage and a stroke-to-hair generation stage. In the stroke parameterization stage, we firstly introduce parametric strokes to approximate the hair wisps, where the stroke shape is controlled by a quadratic Bézier curve and a thickness parameter. Since rendering strokes with thickness to an image is not differentiable, we opt to leverage a neural renderer to construct the mapping from stroke parameters to a stroke image. Thus, the stroke parameters can be directly estimated from hair regions in a differentiable way, enabling us to flexibly edit the hairstyles of input images. In the stroke-to-hair generation stage, we design a hairstyle refinement network that first encodes coarsely composed images of hair strokes, face, and background into latent representations and then generates high-fidelity face images with desirable new hairstyles from the latent codes. Extensive experiments demonstrate that our HairstyleNet achieves state-of-the-art performance and allows flexible hairstyle manipulation.

TeethGNN: Semantic 3D Teeth Segmentation With Graph Neural Networks.

In this paper, we present TeethGNN, a novel 3D tooth segmentation method based on graph neural networks (GNNs). Given a mesh-represented 3D dental model in non-euclidean domain, our method outputs accurate and fine-grained separation of each individual tooth robust to scanning noise, foreign matters (e.g., bubbles, dental accessories, etc.), and even severe malocclusion. Unlike previous CNN-based methods that bypass handling non-euclidean mesh data by reshaping hand-crafted geometric features into regular grids, we explore the non-uniform and irregular structure of mesh itself in its dual space and exploit graph neural networks for effective geometric feature learning. To address the crowded teeth issues and incomplete segmentation that commonly exist in previous methods, we design a two-branch network, one of which predicts a segmentation label for each facet while the other regresses each facet an offset away from its tooth centroid. Clustering are later conducted on offset-shifted locations, enabling both the separation of adjoining teeth and the adjustment of incompletely segmented teeth. Exploiting GNN for directly processing mesh data frees us from extracting hand-crafted feature, and largely speeds up the inference procedure. Extensive experiments have shown that our method achieves the new state-of-the-art results for teeth segmentation and outperforms previous methods both quantitatively and qualitatively.

OrthoAligner: Image-Based Teeth Alignment Prediction via Latent Style Manipulation.

In this article, we present OrthoAligner, a novel method to predict the visual outcome of orthodontic treatment in a portrait image. Unlike the state-of-the-art method, which relies on a 3D teeth model obtained from dental scanning, our method generates realistic alignment effects in images without requiring additional 3D information as input and thus making our system readily available to average users. The key of our approach is to employ the 3D geometric information encoded in an unsupervised generative model, i.e., StyleGAN in this article. Instead of directly conducting translation in the image space, we embed the teeth region extracted from a given portrait to the latent space of the StyleGAN generator and propose a novel latent editing method to discover a geometrically meaningful editing path that yields the alignment process in the image space. To blend the edited mouth region with the original portrait image, we further introduce a BlendingNet to remove boundary artifacts and correct color inconsistency. We also extend our method to short video clips by propagating the alignment effects across neighboring frames. We evaluate our method in various orthodontic cases, compare it to the state-of-the-art and competitive baselines, and validate the effectiveness of each component.

Human Bas-Relief Generation From a Single Photograph.

We present a semi-automatic method for producing human bas-relief from a single photograph. Given an input photo of one or multiple persons, our method first estimates a 3D skeleton for each person in the image. SMPL models are then fitted to the 3D skeletons to generate a 3D guide model. To align the 3D guide model with the image, we compute a 2D warping field to non-rigidly register the projected contours of the guide model with the body contours in the image. Then the normal map of the 3D guide model is warped by the 2D deformation field to reconstruct an overall base shape. Finally, the base shape is integrated with a fine-scale normal map to produce the final bas-relief. To tackle the complex intra- and inter-body interactions, we design an occlusion relationship resolution method that operates at the level of 3D skeletons with minimal user inputs. To tightly register the model contours to the image contours, we propose a non-rigid point matching algorithm harnessing user-specified sparse correspondences. Experiments demonstrate that our human bas-relief generation method is capable of producing perceptually realistic results on various single-person and multi-person images, on which the state-of-the-art depth and pose estimation methods often fail.

Sketch-R2CNN: An RNN-Rasterization-CNN Architecture for Vector Sketch Recognition.

Sketches in existing large-scale datasets like the recent QuickDraw collection are often stored in a vector format, with strokes consisting of sequentially sampled points. However, most existing sketch recognition methods rasterize vector sketches as binary images and then adopt image classification techniques. In this article, we propose a novel end-to-end single-branch network architecture RNN-Rasterization-CNN (Sketch-R2CNN for short) to fully leverage the vector format of sketches for recognition. Sketch-R2CNN takes a vector sketch as input and uses an RNN for extracting per-point features in the vector space. We then develop a neural line rasterization module to convert the vector sketch and the per-point features to multi-channel point feature maps, which are subsequently fed to a CNN for extracting convolutional features in the pixel space. Our neural line rasterization module is designed in a differentiable way for end-to-end learning. We perform experiments on existing large-scale sketch recognition datasets and show that the RNN-Rasterization design brings consistent improvement over CNN baselines and that Sketch-R2CNN substantially outperforms the state-of-the-art methods.

DeepSketchHair: Deep Sketch-Based 3D Hair Modeling.

We present DeepSketchHair, a deep learning based tool for modeling of 3D hair from 2D sketches. Given a 3D bust model as reference, our sketching system takes as input a user-drawn sketch (consisting of hair contour and a few strokes indicating the hair growing direction within a hair region), and automatically generates a 3D hair model, matching the input sketch. The key enablers of our system are three carefully designed neural networks, namely, S2ONet, which converts an input sketch to a dense 2D hair orientation field; O2VNet, which maps the 2D orientation field to a 3D vector field; and V2VNet, which updates the 3D vector field with respect to the new sketches, enabling hair editing with additional sketches in new views. All the three networks are trained with synthetic data generated from a 3D hairstyle database. We demonstrate the effectiveness and expressiveness of our tool using a variety of hairstyles and also compare our method with prior art.

AutoSweep: Recovering 3D Editable Objects from a Single Photograph.

This paper presents a fully automatic framework for extracting editable 3D objects directly from a single photograph. Unlike previous methods which recover either depth maps, point clouds, or mesh surfaces, we aim to recover 3D objects with semantic parts and can be directly edited. We base our work on the assumption that most human-made objects are constituted by parts and these parts can be well represented by generalized primitives. Our work makes an attempt towards recovering two types of primitive-shaped objects, namely, generalized cuboids and generalized cylinders. To this end, we build a novel instance-aware segmentation network for accurate part separation. Our GeoNet outputs a set of smooth part-level masks labeled as profiles and bodies. Then in a key stage, we simultaneously identify profile-body relations and recover 3D parts by sweeping the recognized profile along their body contour and jointly optimize the geometry to align with the recovered masks. Qualitative and quantitative experiments show that our algorithm can recover high quality 3D models and outperforms existing methods in both instance segmentation and 3D reconstruction.

Model-Guided 3D Sketching.

We present a novel 3D model-guided interface for in-situ sketching on 3D planes. Our work is motivated by evolutionary design, where existing 3D objects form the basis for conceptual re-design or further design exploration. We contribute a novel workflow that exploits the geometry of an underlying 3D model to infer 3D planes on which 2D strokes drawn that are on and around the 3D model should be meaningfully projected. This provides users with the nearly modeless fluidity of a sketching interface, and is particularly useful for 3D sketching over planes that are not easily accessible or do not preexist. We also provide an additional set of tools, including sketching with explicit plane selection and model-aware canvas manipulation. Our system is evaluated with a user study, showing that our technique is easy to learn and effective for rapid sketching of product design variations around existing 3D models.

3D Tooth Segmentation and Labeling Using Deep Convolutional Neural Networks.

In this paper, we present a novel approach for 3D dental model segmentation via deep Convolutional Neural Networks (CNNs). Traditional geometry-based methods tend to receive undesirable results due to the complex appearance of human teeth (e.g., missing/rotten teeth, feature-less regions, crowding teeth, extra medical attachments, etc.). Furthermore, labeling of individual tooth is hardly enabled in traditional tooth segmentation methods. To address these issues, we propose to learn a generic and robust segmentation model by exploiting deep Neural Networks, namely NNs. The segmentation task is achieved by labeling each mesh face. We extract a set of geometry features as face feature representations. In the training step, the network is fed with those features, and produces a probability vector, of which each element indicates the probability a face belonging to the corresponding model part. To this end, we extensively experiment with various network structures, and eventually arrive at a 2-level hierarchical CNNs structure for tooth segmentation: one for teeth-gingiva labeling and the other for inter-teeth labeling. Further, we propose a novel boundary-aware tooth simplification method to significantly improve efficiency in the stage of feature extraction. After CNNs prediction, we do graph-based label optimization and further refine the boundary with an improved version of fuzzy clustering. The accuracy of our mesh labeling method exceeds that of the state-of-art geometry-based methods, reaching 99.06 percent measured by area which is directly applicable in orthodontic CAD systems. It is also robust to any possible foreign matters on model surface, e.g., air bubbles, dental accessories, and many more.

Toward Support-free 3D Printing: A Skeletal Approach for Partitioning Models.

Minimizing support structures is crucial in reducing 3D printing material and time. Partition-based methods are efficient means in realizing this objective. Although some algorithms exist for support-free fabrication of solid models, no algorithm ever considers the problem of support-free fabrication for shell models (i.e., hollowed meshes). In this paper, we present a skeleton-based algorithm for partitioning a 3D surface model into the least number of parts for 3D printing without using any support structure. To achieve support-free fabrication while minimizing the effect of the seams and cracks that are inevitably induced by the partition, which affect the aesthetics and strength of the final assembled surface, we put forward an optimization system with the minimization of the number of partitions and the total length of the cuts, under the constraints of support-free printing angle. Our approach is particularly tailored for shell models, and it can be applicable to solid models as well. We first rigorously show that the optimization problem is NP-hard and then propose a stochastic method to find an optimal solution to the objectives. We propose a polynomial-time algorithm for a special case when the skeleton graph satisfies the requirement that the number of partitioned parts and the degree of each node are bounded by a small constant. We evaluate our partition method on a number of 3D models and validate our method by 3D printing experiments.

Recovering Functional Mechanical Assemblies from Raw Scans.

This paper presents a method to reconstruct a functional mechanical assembly from raw scans. Given multiple input scans of a mechanical assembly, our method first extracts the functional mechanical parts using a motion-guided, patch-based hierarchical registration and labeling algorithm. The extracted functional parts are then parameterized from the segments and their internal mechanical relations are encoded by a graph. We use a joint optimization to solve for the best geometry, placement, and orientation of each part, to obtain a final workable mechanical assembly. We demonstrated our algorithm on various types of mechanical assemblies with diverse settings and validated our output using physical fabrication.

Pairwise harmonics for shape analysis.

This paper introduces a simple yet effective shape analysis mechanism for geometry processing. Unlike traditional shape analysis techniques which compute descriptors per surface point up to certain neighborhoods, we introduce a shape analysis framework in which the descriptors are based on pairs of surface points. Such a pairwise analysis approach leads to a new class of shape descriptors that are more global, discriminative, and can effectively capture the variations in the underlying geometry. Specifically, we introduce new shape descriptors based on the isocurves of harmonic functions whose global maximum and minimum occur at the point pair. We show that these shape descriptors can infer shape structures and consistently lead to simpler and more efficient algorithms than the state-of-the-art methods for three applications: intrinsic reflectional symmetry axis computation, matching shape extremities, and simultaneous surface segmentation and skeletonization.

Mesh segmentation with concavity-aware fields.

This paper presents a simple and efficient automatic mesh segmentation algorithm that solely exploits the shape concavity information. The method locates concave creases and seams using a set of concavity-sensitive scalar fields. These fields are computed by solving a Laplacian system with a novel concavity-sensitive weighting scheme. Isolines sampled from the concavity-aware fields naturally gather at concave seams, serving as good cutting boundary candidates. In addition, the fields provide sufficient information allowing efficient evaluation of the candidate cuts. We perform a summarization of all field gradient magnitudes to define a score for each isoline and employ a score-based greedy algorithm to select the best cuts. Extensive experiments and quantitative analysis have shown that the quality of our segmentations are better than or comparable with existing state-of-the-art more complex approaches.

Dot scissor: a single-click interface for mesh segmentation.

This paper presents a very easy-to-use interactive tool, which we call dot scissor, for mesh segmentation. The user's effort is reduced to placing only a single click where a cut is desired. Such a simple interface is made possible by a directional search strategy supported by a concavity-aware harmonic field and a robust voting scheme that selects the best isoline as the cut. With a concavity-aware weighting scheme, the harmonic fields gather dense isolines along concave regions which are natural boundaries of semantic components. The voting scheme relies on an isoline-face scoring mechanism that considers both shape geometry and user intent. We show by extensive experiments and quantitative analysis that our tool advances the state-of-the-art segmentation methods in both simplicity of use and segmentation quality.

Bilateral normal filtering for mesh denoising.

Decoupling local geometric features from the spatial location of a mesh is crucial for feature-preserving mesh denoising. This paper focuses on first order features, i.e., facet normals, and presents a simple yet effective anisotropic mesh denoising framework via normal field denoising. Unlike previous denoising methods based on normal filtering, which process normals defined on the Gauss sphere, our method considers normals as a surface signal defined over the original mesh. This allows the design of a novel bilateral normal filter that depends on both spatial distance and signal distance. Our bilateral filter is a more natural extension of the elegant bilateral filter for image denoising than those used in previous bilateral mesh denoising methods. Besides applying this bilateral normal filter in a local, iterative scheme, as common in most of previous works, we present for the first time a global, noniterative scheme for an isotropic denoising. We show that the former scheme is faster and more effective for denoising extremely noisy meshes while the latter scheme is more robust to irregular surface sampling. We demonstrate that both our feature-preserving schemes generally produce visually and numerically better denoising results than previous methods, especially at challenging regions with sharp features or irregular sampling.

[China's environmental load and environmental depressurization analysis].

Based on material flow accounting and related indicators, an indicator, domestic environmental load, is formulated to measure the aggregate environmental pressure of a nation. Combining this indicator with the gross national product, an indicator for environmental efficiency is derived. The domestic environmental load is then decomposed into the rebound effect caused by economic growth and the depressurization effect induced by the efficiency increase. A case study was carried out for the Chinese economy to investigate its domestic environmental load, environmental efficiency and the rebound and depressurization effects. Results show that the environmental efficiency of the Chinese economy increased during the study period with an annual rate of 5.6%, indicating that a certain degree of depressurization was achieved. However, the rebound effect caused by economic growth was much greater than the depressurization effect induced by the efficiency increase,resulting in a considerable increase in the domestic environmental load (the annual growth rate was 3.8%). The Chinese economy is characterized by high environmental pressure and it is hard to achieve absolute depressurization.