We present a novel learning-based method for predicting tooth movements in orthodontic treatment path planning (orthodontic staging). Recognizing the multi-solution nature of orthodontic staging, our approach involves generating the staging sequence progressively with a dedicated Transformer model. This model predicts teeth movements within a predefined number of steps (e.g., 10 or 20), targeting alignment in problematic dentition. The Transformer refines its predictions iteratively, building on previous outcomes until reaching a state that aligns with the target within an acceptable distance. This mirrors real-life scenarios where orthodontists dynamically adjust staging plans based on treatment outcomes. Our Transformer model is tailored to incorporate spatial and temporal attentions, addressing inter-tooth and inter-step interactions, respectively. These attentions are further refined with relative positional encoding. Recognizing the significant influence of tooth shape on the alignment process, we propose integrating a tooth-wise shape encoder to extract morphological features from the 3D teeth point cloud. These features are then fused into the Transformer, facilitating the capture of inter-tooth dynamics during staging, in collaboration with spatial attention. We validate the proposed method on a large-scale dataset that contains 10K real-life orthodontic cases. The results show that our method outperforms the state-of-the-art, and orthodontists favor its predictions.

It is demanding to author an existing hairstyle for novel characters in games and VR applications. However, it is a non-trivial task for artists due to the complicated hair geometries and spatial interactions to preserve. In this paper, we present an automatic shape adaptation method to retarget 3D hairstyles. We formulate the adaptation process as a constrained optimization problem, where all the shape properties and spatial relationships are converted into individual objectives and constraints. To make such an optimization on high-resolution hairstyles tractable, we adopt a multi-scale strategy to compute the target positions of the hair strands in a coarse-to-fine manner. The global solving for the inter-strands coupling is restricted to the coarse level, and the solving for fine details is made local and parallel. In addition, we present a novel hairline edit tool to allow for user customization during retargeting. We achieve it by solving physics-based deformations of an embedded membrane to redistribute the hair roots with minimal distortion. We demonstrate the efficacy of our method through quantitative and qualitative experiments on various hairstyles and characters.

In this article, we present GCN-Denoiser, a novel feature-preserving mesh denoising method based on graph convolutional networks ( GCNs ). Unlike previous learning-based mesh denoising methods that exploit handcrafted or voxel-based representations for feature learning, our method explores the structure of a triangular mesh itself and introduces a graph representation followed by graph convolution operations in the dual space of triangles. We show such a graph representation naturally captures the geometry features while being lightweight for both training and inference. To facilitate effective feature learning, our network exploits both static and dynamic edge convolutions, which allow us to learn information from both the explicit mesh structure and potential implicit relations among unconnected neighbors. To better approximate an unknown noise function, we introduce a cascaded optimization paradigm to progressively regress the noise-free facet normals with multiple GCNs. GCN-Denoiser achieves the new state-of-the-art results in multiple noise datasets, including CAD models often containing sharp features and raw scan models with real noise captured from different devices. We also create a new dataset called PrintData containing 20 real scans with their corresponding ground-truth meshes for the research community. Our code and data are available at https://github.com/Jhonve/GCN-Denoiser.

Traditionally, reduced hair simulation methods are either restricted to heuristic approximations or bound to specific hairstyles. We introduce the first CNN-integrated framework for simulating various hairstyles. The approach produces visually realistic hairs with an interactive speed. To address the technical challenges, our hair simulation pipeline is designed as a two-stage process. First, we present a fully-convolutional neural interpolator as the backbone generator to compute dynamic weights for guide hair interpolation. Then, we adopt a second generator to produce fine-scale displacements to enhance the hair details. We train the neural interpolator with a dedicated loss function and the displacement generator with an adversarial discriminator. Experimental results demonstrate that our method is effective, efficient, and superior to the state-of-the-art on a wide variety of hairstyles. We further propose a performance-driven digital avatar system and an interactive hairstyle editing tool to illustrate the practical applications.

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.

NNWarp is a highly re-usable and efficient neural network (NN) based nonlinear deformable simulation framework. Unlike other machine learning applications such as image recognition, where different inputs have a uniform and consistent format (e.g., an array of all the pixels in an image), the input for deformable simulation is quite variable, high-dimensional, and parametrization-unfriendly. Consequently, even though the neural network is known for its rich expressivity of nonlinear functions, directly using an NN to reconstruct the force-displacement relation for general deformable simulation is nearly impossible. NNWarp obviates this difficulty by partially restoring the force-displacement relation via warping the nodal displacement simulated using a simplistic constitutive model-the linear elasticity. In other words, NNWarp yields an incremental displacement fix per mesh node based on a simplified (therefore incorrect) simulation result other than synthesizing the unknown displacement directly. We introduce a compact yet effective feature vector including geodesic, potential and digression to sort training pairs of per-node linear and nonlinear displacement. NNWarp is robust under different model shapes and tessellations. With the assistance of deformation substructuring, one NN training is able to handle a wide range of 3D models of various geometries. Thanks to the linear elasticity and its constant system matrix, the underlying simulator only needs to perform one pre-factorized matrix solve at each time step, which allows NNWarp to simulate large models in real time.

Stress analysis is a crucial tool for designing structurally sound shapes. However, the expensive computational cost has hampered its use in interactive shape editing tasks. We augment the existing example-based shape editing tools, and propose a fast subspace stress analysis method to enable stress-aware shape editing. In particular, we construct a reduced stress basis from a small set of shape exemplars and possible external forces. This stress basis is automatically adapted to the current user edited shape on the fly, and thereby offers reliable stress estimation. We then introduce a new finite element discretization scheme to use the reduced basis for fast stress analysis. Our method runs up to two orders of magnitude faster than the full-space finite element analysis, with average L2estimation errors less than 2 percent and maximum L2errors less than 6 percent. Furthermore, we build an interactive stress-aware shape editing tool to demonstrate its performance in practice.

Recent interior carving methods for functional design necessitate a cumbersome cut-and-glue process in fabrication. We propose a method to generate interior voids which not only satisfy the functional purposes but are also support-free during the 3D printing process. We introduce a support-free unit structure for voxelization and derive the wall thicknesses parametrization for continuous optimization. We also design a discrete dithering algorithm to ensure the printability of ghost voxels. The interior voids are iteratively carved by alternating the optimization and dithering. We apply our method to optimize the static and rotational stability, and print various results to evaluate the efficacy.

Joint channel-aware and buffer-aware scheduling is a promising way to improve Quality of Service (QoS) given energy efficiency constraint. In this paper, optimal probabilistic scheduling strategy with random data arrival and fading channel is analysed. More specifically, we focus on the fast fading scenario where a data packet has to be transmitted with several timeslots. A linear programming problem is formulated, where we minimize the average delay given an average power constraint. By deriving the analytical solution to this linear programming, optimal delay-power tradeoff along with the corresponding threshold-based scheduling policy is presented.

Model classification is essential to the management and reuse of 3D CAD models. Manual model classification is laborious and error prone. At the same time, the automatic classification methods are scarce due to the intrinsic complexity of 3D CAD models. In this paper, we propose an automatic 3D CAD model classification approach based on deep neural networks. According to prior knowledge of the CAD domain, features are selected and extracted from 3D CAD models first, and then preprocessed as high dimensional input vectors for category recognition. By analogy with the thinking process of engineers, a deep neural network classifier for 3D CAD models is constructed with the aid of deep learning techniques. To obtain an optimal solution, multiple strategies are appropriately chosen and applied in the training phase, which makes our classifier achieve better performance. We demonstrate the efficiency and effectiveness of our approach through experiments on 3D CAD model datasets.

Inverse shape design for elastic objects greatly eases the design efforts by letting users focus on desired target shapes without thinking about elastic deformations. Solving this problem using classic iterative methods (e.g., Newton-Raphson methods), however, often suffers from slow convergence toward a desired solution. In this paper, we propose an asymptotic numerical method that exploits the underlying mathematical structure of specific nonlinear material models, and thus runs orders of magnitude faster than traditional Newton-type methods. We apply this method to compute rest shapes for elastic fabrication, where the rest shape of an elastic object is computed such that after physical fabrication the real object deforms into a desired shape. We illustrate the performance and robustness of our method through a series of elastic fabrication experiments.

Images are static and lack important depth information about the underlying 3D scenes. We introduceinteractive imagesin the context of man-made environments wherein objects are simple and regular, share various non-local relations (e.g., coplanarity, parallelism, etc.), and are often repeated. Our interactive framework creates partial scene reconstructions based on cuboid-proxies with minimal user interaction. It subsequently allows a range of intuitive image edits mimicking real-world behavior, which are otherwise difficult to achieve. Effectively, the user simply provides high-level semantic hints, while our system ensures plausible operations by conforming to the extracted non-local relations. We demonstrate our system on a range of real-world images and validate the plausibility of the results using a user study.

While many approaches have been developed to visualize 3D city scenes, most of them exhibit the visualization results in a uniform rendering style. This paper presents an expressive rendering approach for visualizing large-scale 3D city scenes with various rendering styles integrated in a seamless way. Each view is actually a combination of the photorealistic rendering, the nonphotorealistic rendering, and the line drawing, so as to highlight the information that is interesting for the users and de-emphasize the other that is less important. At run-time, the users are allowed to specify their interested locations with pre-determined 3D landmarks. Our system automatically computes the salience of each location and visualize the entire scene with emphasis in the area of interests. The GPU-based implementation enables real-time performance, and demonstrates outstanding practicality.

Exchange of procedural CAD models between heterogeneous CAD systems is still a challenging issue in CAD area. Previously we proposed an approach for effectively constructing synchronized collaborative design environment based on heterogeneous CAD systems. In this paper, we extend the synchronized collaborative design environment that we have developed to a Web services based platform for exchange of procedural CAD models between heterogeneous CAD systems. First, the real-time exchange of a single operation is extended to the exchange of the complete procedural CAD model between heterogeneous CAD systems. Furthermore, Web services technology is adopted to encapsulate the procedural CAD model exchange functions, which are then released on the Internet as a standard interface and can be used by remote developers in their windows applications, Web applications, and so on. Finally, a Web service for exchange of procedural CAD models between SolidWorks and Autodesk Mechanical Desktop is realized.