94 results
Search Results
Now showing 1 - 10 of 94
Item Quad Layouts via Constrained T-Mesh Quantization(The Eurographics Association and John Wiley & Sons Ltd., 2021) Lyon, Max; Campen, Marcel; Kobbelt, Leif; Mitra, Niloy and Viola, IvanWe present a robust and fast method for the creation of conforming quad layouts on surfaces. Our algorithm is based on the quantization of a T-mesh, i.e. an assignment of integer lengths to the sides of a non-conforming rectangular partition of the surface. This representation has the benefit of being able to encode an infinite number of layout connectivity options in a finite manner, which guarantees that a valid layout can always be found. We carefully construct the T-mesh from a given seamless parametrization such that the algorithm can provide guarantees on the results' quality. In particular, the user can specify a bound on the angular deviation of layout edges from prescribed directions. We solve an integer linear program (ILP) to find a coarse quad layout adhering to that maximal deviation. Our algorithm is guaranteed to yield a conforming quad layout free of T-junctions together with bounded angle distortion. Our results show that the presented method is fast, reliable, and achieves high quality layouts.Item Stable and Efficient Differential Estimators on Oriented Point Clouds(The Eurographics Association and John Wiley & Sons Ltd., 2021) Lejemble, Thibault; Coeurjolly, David; Barthe, Loïc; Mellado, Nicolas; Digne, Julie and Crane, KeenanPoint clouds are now ubiquitous in computer graphics and computer vision. Differential properties of the point-sampled surface, such as principal curvatures, are important to estimate in order to locally characterize the scanned shape. To approximate the surface from unstructured points equipped with normal vectors, we rely on the Algebraic Point Set Surfaces (APSS) [GG07] for which we provide convergence and stability proofs for the mean curvature estimator. Using an integral invariant viewpoint, this first contribution links the algebraic sphere regression involved in the APSS algorithm to several surface derivatives of different orders. As a second contribution, we propose an analytic method to compute the shape operator and its principal curvatures from the fitted algebraic sphere. We compare our method to the state-of-the-art with several convergence and robustness tests performed on a synthetic sampled surface. Experiments show that our curvature estimations are more accurate and stable while being faster to compute compared to previous methods. Our differential estimators are easy to implement with little memory footprint and only require a unique range neighbors query per estimation. Its highly parallelizable nature makes it appropriate for processing large acquired data, as we show in several real-world experiments.Item Towards a Neural Graphics Pipeline for Controllable Image Generation(The Eurographics Association and John Wiley & Sons Ltd., 2021) Chen, Xuelin; Cohen-Or, Daniel; Chen, Baoquan; Mitra, Niloy J.; Mitra, Niloy and Viola, IvanIn this paper, we leverage advances in neural networks towards forming a neural rendering for controllable image generation, and thereby bypassing the need for detailed modeling in conventional graphics pipeline. To this end, we present Neural Graphics Pipeline (NGP), a hybrid generative model that brings together neural and traditional image formation models. NGP decomposes the image into a set of interpretable appearance feature maps, uncovering direct control handles for controllable image generation. To form an image, NGP generates coarse 3D models that are fed into neural rendering modules to produce view-specific interpretable 2D maps, which are then composited into the final output image using a traditional image formation model. Our approach offers control over image generation by providing direct handles controlling illumination and camera parameters, in addition to control over shape and appearance variations. The key challenge is to learn these controls through unsupervised training that links generated coarse 3D models with unpaired real images via neural and traditional (e.g., Blinn- Phong) rendering functions, without establishing an explicit correspondence between them. We demonstrate the effectiveness of our approach on controllable image generation of single-object scenes. We evaluate our hybrid modeling framework, compare with neural-only generation methods (namely, DCGAN, LSGAN, WGAN-GP, VON, and SRNs), report improvement in FID scores against real images, and demonstrate that NGP supports direct controls common in traditional forward rendering. Code is available at http://geometry.cs.ucl.ac.uk/projects/2021/ngp.Item LoBSTr: Real-time Lower-body Pose Prediction from Sparse Upper-body Tracking Signals(The Eurographics Association and John Wiley & Sons Ltd., 2021) Yang, Dongseok; Kim, Doyeon; Lee, Sung-Hee; Mitra, Niloy and Viola, IvanWith the popularization of games and VR/AR devices, there is a growing need for capturing human motion with a sparse set of tracking data. In this paper, we introduce a deep neural network (DNN) based method for real-time prediction of the lowerbody pose only from the tracking signals of the upper-body joints. Specifically, our Gated Recurrent Unit (GRU)-based recurrent architecture predicts the lower-body pose and feet contact states from a past sequence of tracking signals of the head, hands, and pelvis. A major feature of our method is that the input signal is represented by the velocity of tracking signals. We show that the velocity representation better models the correlation between the upper-body and lower-body motions and increases the robustness against the diverse scales and proportions of the user body than position-orientation representations. In addition, to remove foot-skating and floating artifacts, our network predicts feet contact state, which is used to post-process the lower-body pose with inverse kinematics to preserve the contact. Our network is lightweight so as to run in real-time applications. We show the effectiveness of our method through several quantitative evaluations against other architectures and input representations with respect to wild tracking data obtained from commercial VR devices.Item Write Like You: Synthesizing Your Cursive Online Chinese Handwriting via Metric-based Meta Learning(The Eurographics Association and John Wiley & Sons Ltd., 2021) Tang, Shusen; Lian, Zhouhui; Mitra, Niloy and Viola, IvanIn this paper, we propose a novel Sequence-to-Sequence model based on metric-based meta learning for the arbitrary style transfer of online Chinese handwritings. Unlike most existing methods that treat Chinese handwritings as images and are unable to reflect the human writing process, the proposed model directly handles sequential online Chinese handwritings. Generally, our model consists of three sub-models: a content encoder, a style encoder and a decoder, which are all Recurrent Neural Networks. In order to adaptively obtain the style information, we introduce an attention-based adaptive style block which has been experimentally proven to bring considerable improvement to our model. In addition, to disentangle the latent style information from characters written by any writers effectively, we adopt metric-based meta learning and pre-train the style encoder using a carefully-designed discriminative loss function. Then, our entire model is trained in an end-to-end manner and the decoder adaptively receives the style information from the style encoder and the content information from the content encoder to synthesize the target output. Finally, by feeding the trained model with a content character and several characters written by a given user, our model can write that Chinese character in the user's handwriting style by drawing strokes one by one like humans. That is to say, as long as you write several Chinese character samples, our model can imitate your handwriting style when writing. In addition, after fine-tuning the model with a few samples, it can generate more realistic handwritings that are difficult to be distinguished from the real ones. Both qualitative and quantitative experiments demonstrate the effectiveness and superiority of our method.Item Implicit Modeling of Patient-Specific Aortic Dissections with Elliptic Fourier Descriptors(The Eurographics Association and John Wiley & Sons Ltd., 2021) Mistelbauer, Gabriel; Rössl, Christian; Bäumler, Kathrin; Preim, Bernhard; Fleischmann, Dominik; Borgo, Rita and Marai, G. Elisabeta and Landesberger, Tatiana vonAortic dissection is a life-threatening vascular disease characterized by abrupt formation of a new flow channel (false lumen) within the aortic wall. Survivors of the acute phase remain at high risk for late complications, such as aneurysm formation, rupture, and death. Morphologic features of aortic dissection determine not only treatment strategies in the acute phase (surgical vs. endovascular vs. medical), but also modulate the hemodynamics in the false lumen, ultimately responsible for late complications. Accurate description of the true and false lumen, any communications across the dissection membrane separating the two lumina, and blood supply from each lumen to aortic branch vessels is critical for risk prediction. Patient-specific surface representations are also a prerequisite for hemodynamic simulations, but currently require time-consuming manual segmentation of CT data. We present an aortic dissection cross-sectional model that captures the varying aortic anatomy, allowing for reliable measurements and creation of high-quality surface representations. In contrast to the traditional spline-based cross-sectional model, we employ elliptic Fourier descriptors, which allows users to control the accuracy of the cross-sectional contour of a flow channel. We demonstrate (i) how our approach can solve the requirements for generating surface and wall representations of the flow channels, (ii) how any number of communications between flow channels can be specified in a consistent manner, and (iii) how well branches connected to the respective flow channels are handled. Finally, we discuss how our approach is a step forward to an automated generation of surface models for aortic dissections from raw 3D imaging segmentation masks.Item Adversarial Single-Image SVBRDF Estimation with Hybrid Training(The Eurographics Association and John Wiley & Sons Ltd., 2021) Zhou, Xilong; Kalantari, Nima Khademi; Mitra, Niloy and Viola, IvanIn this paper, we propose a deep learning approach for estimating the spatially-varying BRDFs (SVBRDF) from a single image. Most existing deep learning techniques use pixel-wise loss functions which limits the flexibility of the networks in handling this highly unconstrained problem. Moreover, since obtaining ground truth SVBRDF parameters is difficult, most methods typically train their networks on synthetic images and, therefore, do not effectively generalize to real examples. To avoid these limitations, we propose an adversarial framework to handle this application. Specifically, we estimate the material properties using an encoder-decoder convolutional neural network (CNN) and train it through a series of discriminators that distinguish the output of the network from ground truth. To address the gap in data distribution of synthetic and real images, we train our network on both synthetic and real examples. Specifically, we propose a strategy to train our network on pairs of real images of the same object with different lighting. We demonstrate that our approach is able to handle a variety of cases better than the state-of-the-art methods.Item Moving Basis Decomposition for Precomputed Light Transport(The Eurographics Association and John Wiley & Sons Ltd., 2021) Silvennoinen, Ari; Sloan, Peter-Pike; Bousseau, Adrien and McGuire, MorganWe study the problem of efficient representation of potentially high-dimensional, spatially coherent signals in the context of precomputed light transport. We present a basis decomposition framework, Moving Basis Decomposition (MBD), that generalizes many existing basis expansion methods and enables high-performance, seamless reconstruction of compressed data. We develop an algorithm for solving large-scale MBD problems. We evaluate MBD against state-of-the-art in a series of controlled experiments and describe a real-world application, where MBD serves as the backbone of a scalable global illumination system powering multiple, current and upcoming 60Hz AAA-titles running on a wide range of hardware platforms.Item The Diamond Laplace for Polygonal and Polyhedral Meshes(The Eurographics Association and John Wiley & Sons Ltd., 2021) Bunge, Astrid; Botsch, Mario; Alexa, Marc; Digne, Julie and Crane, KeenanWe introduce a construction for discrete gradient operators that can be directly applied to arbitrary polygonal surface as well as polyhedral volume meshes. The main idea is to associate the gradient of functions defined at vertices of the mesh with diamonds: the region spanned by a dual edge together with its corresponding primal element - an edge for surface meshes and a face for volumetric meshes. We call the operator resulting from taking the divergence of the gradient Diamond Laplacian. Additional vertices used for the construction are represented as affine combinations of the original vertices, so that the Laplacian operator maps from values at vertices to values at vertices, as is common in geometry processing applications. The construction is local, exactly the same for all types of meshes, and results in a symmetric negative definite operator with linear precision. We show that the accuracy of the Diamond Laplacian is similar or better compared to other discretizations. The greater versatility and generally good behavior come at the expense of an increase in the number of non-zero coefficients that depends on the degree of the mesh elements.Item UprightRL: Upright Orientation Estimation of 3D Shapes via Reinforcement Learning(The Eurographics Association and John Wiley & Sons Ltd., 2021) Chen, Luanmin; Xu, Juzhan; Wang, Chuan; Huang, Haibin; Huang, Hui; Hu, Ruizhen; Zhang, Fang-Lue and Eisemann, Elmar and Singh, KaranIn this paper, we study the problem of 3D shape upright orientation estimation from the perspective of reinforcement learning, i.e. we teach a machine (agent) to orientate 3D shapes step by step to upright given its current observation. Unlike previous methods, we take this problem as a sequential decision-making process instead of a strong supervised learning problem. To achieve this, we propose UprightRL, a deep network architecture designed for upright orientation estimation. UprightRL mainly consists of two submodules: an Actor module and a Critic module which can be learned with a reinforcement learning manner. Specifically, the Actor module selects an action from the action space to perform a point cloud transformation and obtain the new point cloud for the next environment state, while the Critic module evaluates the strategy and guides the Actor to choose the next stage action. Moreover, we design a reward function that encourages the agent to select action which is conducive to orient model towards upright orientation with a positive reward and negative otherwise. We conducted extensive experiments to demonstrate the effectiveness of the proposed model, and experimental results show that our network outperforms the stateof- the-art. We also apply our method to the robot grasping-and-placing experiment, to reveal the practicability of our method.