37-Issue 7

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2632664

Browse

Now showing 1 - 20 of 43

Automatic Mechanism Modeling from a Single Image with CNNs
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Lin, Minmin; Shao, Tianjia; Zheng, Youyi; Ren, Zhong; Weng, Yanlin; Yang, Yin; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
This paper presents a novel system that enables a fully automatic modeling of both 3D geometry and functionality of a mechanism assembly from a single RGB image. The resulting 3D mechanism model highly resembles the one in the input image with the geometry, mechanical attributes, connectivity, and functionality of all the mechanical parts prescribed in a physically valid way. This challenging task is realized by combining various deep convolutional neural networks to provide high-quality and automatic part detection, segmentation, camera pose estimation and mechanical attributes retrieval for each individual part component. On the top of this, we use a local/global optimization algorithm to establish geometric interdependencies among all the parts while retaining their desired spatial arrangement. We use an interaction graph to abstract the inter-part connection in the resulting mechanism system. If an isolated component is identified in the graph, our system enumerates all the possible solutions to restore the graph connectivity, and outputs the one with the smallest residual error. We have extensively tested our system with a wide range of classic mechanism photos, and experimental results show that the proposed system is able to build high-quality 3D mechanism models without user guidance.
Binocular Tone Mapping with Improved Overall Contrast and Local Details
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Zhang, Zhuming; Hu, Xinghong; Liu, Xueting; Wong, Tien-Tsin; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Tone mapping is a commonly used technique that maps the set of colors in high-dynamic-range (HDR) images to another set of colors in low-dynamic-range (LDR) images, to fit the need for print-outs, LCD monitors and projectors. Unfortunately, during the compression of dynamic range, the overall contrast and local details generally cannot be preserved simultaneously. Recently, with the increased use of stereoscopic devices, the notion of binocular tone mapping has been proposed in the existing research study. However, the existing research lacks the binocular perception study and is unable to generate the optimal binocular pair that presents the most visual content. In this paper, we propose a novel perception-based binocular tone mapping method, that can generate an optimal binocular image pair (generating left and right images simultaneously) from an HDR image that presents the most visual content by designing a binocular perception metric. Our method outperforms the existing method in terms of both visual and time performance.
Biorthogonal Wavelet Surface Reconstruction Using Partial Integrations
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Ren, Xiaohua; Lyu, Luan; He, Xiaowei; Cao, Wei; Yang, Zhixin; Sheng, Bin; Zhang, Yanci; Wu, Enhua; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
We introduce a new biorthogonal wavelet approach to creating a water-tight surface defined by an implicit function, from a finite set of oriented points. Our approach aims at addressing problems with previous wavelet methods which are not resilient to missing or nonuniformly sampled data. To address the problems, our approach has two key elements. First, by applying a three-dimensional partial integration, we derive a new integral formula to compute the wavelet coefficients without requiring the implicit function to be an indicator function. It can be shown that the previously used formula is a special case of our formula when the integrated function is an indicator function. Second, a simple yet general method is proposed to construct smooth wavelets with small support. With our method, a family of wavelets can be constructed with the same support size as previously used wavelets while having one more degree of continuity. Experiments show that our approach can robustly produce results comparable to those produced by the Fourier and Poisson methods, regardless of the input data being noisy, missing or nonuniform. Moreover, our approach does not need to compute global integrals or solve large linear systems.
Controlling Stroke Size in Fast Style Transfer with Recurrent Convolutional Neural Network
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Yang, Lingchen; Yang, Lumin; Zhao, Mingbo; Zheng, Youyi; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Controlling stroke size in Fast Style Transfer remains a difficult task. So far, only a few attempts have been made towards it, and they still exhibit several deficiencies regarding efficiency, flexibility, and diversity. In this paper, we aim to tackle these problems and propose a recurrent convolutional neural subnetwork, which we call recurrent stroke-pyramid, to control the stroke size in Fast Style Transfer. Compared to the state-of-the-art methods, our method not only achieves competitive results with much fewer parameters but provides more flexibility and efficiency for generalizing to unseen larger stroke size and being able to produce a wide range of stroke sizes with only one residual unit. We further embed the recurrent stroke-pyramid into the Multi-Styles and the Arbitrary-Style models, achieving both style and stroke-size control in an entirely feed-forward manner with two novel run-time control strategies.
Curvature Continuity Conditions Between Adjacent Toric Surface Patches
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Sun, Lanyin; Zhu, Chungang; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Toric surface patch is the multi-sided generalization of classical Bézier surface patch. Geometric continuity of the parametric surface patches plays a crucial role in geometric modeling. In this paper, the necessary and sufficient conditions of curvature continuity between toric surface patches are illustrated with the theory of toric degeneration. Furthermore, some practical sufficient conditions of curvature continuity of toric surface patches are also developed.
Decomposing Images into Layers with Advanced Color Blending
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Koyama, Yuki; Goto, Masataka; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Digital paintings are often created by compositing semi-transparent layers using various advanced color-blend modes, such as ''color-burn,'' ''multiply,'' and ''screen,'' which can produce interesting non-linear color effects. We propose a method of decomposing an input image into layers with such advanced color blending. Unlike previous layer-decomposition methods, which typically support only linear color-blend modes, ours can handle any user-specified color-blend modes. To enable this, we generalize a previous color-unblending formulation, in which only a specific layering model was considered. We also introduce several techniques for adapting our generalized formulation to practical use, such as the post-processing for refining smoothness. Our method lets users explore possible decompositions to find the one that matches for their purposes by manipulating the target color-blend mode and desired color distribution for each layer, as well as the number of layers. Thus, the output of our method is a layered, easily editable image composition organized in a way that digital artists are familiar with. Our method is useful for remixing existing illustrations, flexibly editing single-layer paintings, and bringing physically painted media (e.g., oil paintings) into a digital workflow.
Deep Video Stabilization Using Adversarial Networks
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Xu, Sen-Zhe; Hu, Jun; Wang, Miao; Mu, Tai-Jiang; Hu, Shi-Min; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Video stabilization is necessary for many hand-held shot videos. In the past decades, although various video stabilization methods were proposed based on the smoothing of 2D, 2.5D or 3D camera paths, hardly have there been any deep learning methods to solve this problem. Instead of explicitly estimating and smoothing the camera path, we present a novel online deep learning framework to learn the stabilization transformation for each unsteady frame, given historical steady frames. Our network is composed of a generative network with spatial transformer networks embedded in different layers, and generates a stable frame for the incoming unstable frame by computing an appropriate affine transformation. We also introduce an adversarial network to determine the stability of a piece of video. The network is trained directly using the pair of steady and unsteady videos. Experiments show that our method can produce similar results as traditional methods, moreover, it is capable of handling challenging unsteady video of low quality, where traditional methods fail, such as video with heavy noise or multiple exposures. Our method runs in real time, which is much faster than traditional methods.
Defocus and Motion Blur Detection with Deep Contextual Features
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Kim, Beomseok; Son, Hyeongseok; Park, Seong-Jin; Cho, Sunghyun; Lee, Seungyong; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
We propose a novel approach for detecting two kinds of partial blur, defocus and motion blur, by training a deep convolutional neural network. Existing blur detection methods concentrate on designing low-level features, but those features have difficulty in detecting blur in homogeneous regions without enough textures or edges. To handle such regions, we propose a deep encoder-decoder network with long residual skip-connections and multi-scale reconstruction loss functions to exploit high-level contextual features as well as low-level structural features. Another difficulty in partial blur detection is that there are no available datasets with images having both defocus and motion blur together, as most existing approaches concentrate only on either defocus or motion blur. To resolve this issue, we construct a synthetic dataset that consists of complex scenes with both types of blur. Experimental results show that our approach effectively detects and classifies blur, outperforming other state-of-the-art methods. Our method can be used for various applications, such as photo editing, blur magnification, and deblurring.
Directing the Photography: Combining Cinematic Rules, Indirect Light Controls and Lighting-by-Example
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Galvane, Quentin; Lino, Christophe; Christie, Marc; Cozot, Rémi; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
The placement of lights in a 3D scene is a technical and artistic task that requires time and trained skills. Most 3D modelling tools only provide a direct control of light sources, through the manipulation of parameters such as size, location, flux (the perceived power of light) or opening angle (the light frustum). Approaches have been relying on automated or semi-automated techniques to relieve users from such low-level manipulations at the expense of an important computational cost. In this paper, guided by discussions with experts in scene and object lighting, we propose an indirect control of area light sources. We first formalize the classical 3-point lighting design principle (key-light, fill-lights and back/rim-lights) in a parametric model. Given a key-light placed in the scene, we then provide a computational approach to (i) automatically compute the position and size of fill-lights and back/rim-lights by analyzing the geometry of 3D character, and (ii) automatically compute the flux and size of key, fill and back/rim lights, given a sample reference image in a computationally efficient way. Results demonstrate the benefits of the approach on the quick lighting of 3D characters, and further demonstrate the feasibility of interactive control of multiple lights through image features.
DMAT: Deformable Medial Axis Transform for Animated Mesh Approximation
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Yang, Baorong; Yao, Junfeng; Guo, Xiaohu; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Extracting a faithful and compact representation of an animated surface mesh is an important problem for computer graphics. However, the surface-based methods have limited approximation power for volume preservation when the animated sequences are extremely simplified. In this paper, we introduce Deformable Medial Axis Transform (DMAT), which is deformable medial mesh composed of a set of animated spheres. Starting from extracting an accurate and compact representation of a static MAT as the template and partitioning the vertices on the input surface as the correspondences for each medial primitive, we present a correspondence-based approximation method equipped with an As-Rigid-As-Possible (ARAP) deformation energy defined on medial primitives. As a result, our algorithm produces DMAT with consistent connectivity across the whole sequence, accurately approximating the input animated surfaces.
Dynamic Deep Octree for High-resolution Volumetric Painting in Virtual Reality
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Kim, Yeojin; Kim, Byungmoon; Kim, Young J.; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
With virtual reality, digital painting on 2D canvas is now being extended to 3D space. In this paper, we generalize the 2D pixel canvas to a 3D voxel canvas to allow artists to synthesize volumetric color fields. We develop a deep and dynamic octree-based painting and rendering system using both CPU and GPU to take advantage of the characteristics of both processors (CPU for octree modeling and GPU for volume rendering). On the CPU-side, we dynamically adjust an octree and incrementally update the octree to GPU with low latency without compromising the frame rates of the rendering. Our octree is balanced and uses a novel 3-neighbor connectivity for format simplicity and efficient storage, while allowing constant neighbor access time in ray casting. To further reduce the GPU-side 3-neighbor computations, we precompute a culling mask in CPU and upload it to GPU. Finally, we analyze the numerical error-propagation in ray casting through high resolution octree and present a theoretical error bound.
Ellipsoid Packing Structures on Freeform Surfaces
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Xu, Qun-Ce; Deng, Bailin; Yang, Yong-Liang; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Designers always get good inspirations from fascinating geometric structures gifted by the nature. In the recent years, various computational design tools have been proposed to help generate cell packing structures on freeform surfaces, which consist of a packing of simple primitives, such as polygons, spheres, etc. In this work, we aim at computationally generating novel ellipsoid packing structures on freeform surfaces. We formulate the problem as a generalization of sphere packing structures in the sense that anisotropic ellipsoids are used instead of isotropic spheres to pack a given surface. This is done by defining an anisotropic metric based on local surface anisotropy encoded by principal curvatures and the corresponding directions. We propose an optimization framework that can optimize the shapes of individual ellipsoids and the spatial relation between neighboring ellipsoids to form a quality packing structure. A tailored anisotropic remeshing method is also employed to better initialize the optimization and ensure the quality of the result. Our framework is extensively evaluated by optimizing ellipsoid packing and generating appealing geometric structures on a variety of freeform surfaces.
FashionGAN: Display your fashion design using Conditional Generative Adversarial Nets
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Cui, Yi Rui; Liu, Qi; Gao, Cheng Ying; Su, Zhuo; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Virtual garment display plays an important role in fashion design for it can directly show the design effect of the garment without having to make a sample garment like traditional clothing industry. In this paper, we propose an end-to-end virtual garment display method based on Conditional Generative Adversarial Networks. Different from existing 3D virtual garment methods which need complex interactions and domain-specific user knowledge, our method only need users to input a desired fashion sketch and a specified fabric image then the image of the virtual garment whose shape and texture are consistent with the input fashion sketch and fabric image can be shown out quickly and automatically. Moreover, it can also be extended to contour images and garment images, which further improves the reuse rate of fashion design. Compared with the existing image-to-image methods, the quality of images generated by our method is better in terms of color and shape.
Fast Global Illumination with Discrete Stochastic Microfacets Using a Filterable Model
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Wang, Beibei; Wang, Lu; Holzschuch, Nicolas; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Many real-life materials have a sparkling appearance, whether by design or by nature. Examples include metallic paints, sparkling varnish but also snow. These sparkles correspond to small, isolated, shiny particles reflecting light in a specific direction, on the surface or embedded inside the material. The particles responsible for these sparkles are usually small and discontinuous. These characteristics make it diffcult to integrate them effciently in a standard rendering pipeline, especially for indirect illumination. Existing approaches use a 4-dimensional hierarchy, searching for light-reflecting particles simultaneously in space and direction. The approach is accurate, but still expensive. In this paper, we show that this 4-dimensional search can be approximated using separate 2-dimensional steps. This approximation allows fast integration of glint contributions for large footprints, reducing the extra cost associated with glints be an order of magnitude.
Feature Generation for Adaptive Gradient-Domain Path Tracing
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Back, Jonghee; Yoon, Sung-Eui; Moon, Bochang; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
In this paper, we propose a new technique to incorporate recent adaptive rendering approaches built upon local regression theory into a gradient-domain path tracing framework, in order to achieve high-quality rendering results. Our method aims to reduce random artifacts introduced by random sampling on image colors and gradients. Our high-level approach is to identify a feature image from noisy gradients, and pass the image to an existing local regression based adaptive method so that adaptive sampling and reconstruction using our feature can boost the performance of gradient-domain rendering. To fulfill our idea, we derive an ideal feature in the form of image gradients and propose an estimation process for the ideal feature in the presence of noise in image gradients. We demonstrate that our integrated adaptive solution leads to performance improvement for a gradient-domain path tracer, by seamlessly incorporating recent adaptive sampling and reconstruction strategies through our estimated feature.
Few-shot Learning of Homogeneous Human Locomotion Styles
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Mason, Ian; Starke, Sebastian; Zhang, He; Bilen, Hakan; Komura, Taku; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Using neural networks for learning motion controllers from motion capture data is becoming popular due to the natural and smooth motions they can produce, the wide range of movements they can learn and their compactness once they are trained. Despite these advantages, these systems require large amounts of motion capture data for each new character or style of motion to be generated, and systems have to undergo lengthy retraining, and often reengineering, to get acceptable results. This can make the use of these systems impractical for animators and designers and solving this issue is an open and rather unexplored problem in computer graphics. In this paper we propose a transfer learning approach for adapting a learned neural network to characters that move in different styles from those on which the original neural network is trained. Given a pretrained character controller in the form of a Phase-Functioned Neural Network for locomotion, our system can quickly adapt the locomotion to novel styles using only a short motion clip as an example. We introduce a canonical polyadic tensor decomposition to reduce the amount of parameters required for learning from each new style, which both reduces the memory burden at runtime and facilitates learning from smaller quantities of data. We show that our system is suitable for learning stylized motions with few clips of motion data and synthesizing smooth motions in real-time.
Frontmatter: Pacific Graphics 2018
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Fu, Hongbo; Ghosh, Abhijeet; Kopf, Johannes; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Generative Adversarial Image Super-Resolution Through Deep Dense Skip Connections
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Zhu, Xiaobin; Li, Zhuangzi; Zhang, Xiaoyu; Li, Haisheng; Xue, Ziyu; Wang, Lei; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
Recently, image super-resolution works based on Convolutional Neural Networks (CNNs) and Generative Adversarial Nets (GANs) have shown promising performance. However, these methods tend to generate blurry and over-smoothed super-resolved (SR) images, due to the incomplete loss function and powerless architectures of networks. In this paper, a novel generative adversarial image super-resolution through deep dense skip connections (GSR-DDNet), is proposed to solve the above-mentioned problems. It aims to take advantage of GAN's ability of modeling data distributions, so that GSR-DDNet can select informative feature representation and model the mapping across the low-quality and high-quality images in an adversarial way. The pipeline of the proposed method consists of three main components: 1) The generator of a novel dense skip connection network with the deep structure for learning robust mapping function is proposed to generate SR images from low-resolution images; 2) The feature extraction network based on VGG-19 is adopted to capture high frequency feature maps for content loss; and 3) The discriminator with Wasserstein distance is adopted to identify the overall style of SR and ground-truth images. Experiments conducted on four publicly available datasets demonstrate the superiority against the state-of-the-art methods.
GPU-based Polynomial Finite Element Matrix Assembly for Simplex Meshes
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Mueller-Roemer, Johannes Sebastian; Stork, André; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
In this paper, we present a matrix assembly technique for arbitrary polynomial order finite element simulations on simplex meshes for graphics processing units (GPU). Compared to the current state of the art in GPU-based matrix assembly, we avoid the need for an intermediate sparse matrix and perform assembly directly into the final, GPU-optimized data structure. Thereby, we avoid the resulting 180% to 600% memory overhead, depending on polynomial order, and associated allocation time, while simplifying the assembly code and using a more compact mesh representation. We compare our method with existing algorithms and demonstrate significant speedups.
Improved Use of LOP for Curve Skeleton Extraction
(The Eurographics Association and John Wiley & Sons Ltd., 2018) Li, Lei; Wang, Wencheng; Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes
It remains a challenge to robustly and rapidly extract high quality curve skeletons from 3D models of closed surfaces, especially when there are nearby surface sheets. In this paper, we address this challenge by improving the use of LOP (Locally Optimal Projection) to adaptively contract medial surfaces of 3D models. LOP was originally designed to optimize a raw scanned point cloud to its corresponding geometry surface. It has the effect of contraction, and the contraction amplitude is controlled by a support radius. Our improvements are twofold. First, we constrain the LOP operator applied in the 2D medial surface instead of in the 3D space and take a local region growing strategy to find neighborhoods for implementing LOP. Thus, we avoid interference between disconnected surface parts and accelerate the process due to the reduced search space. Second, we adaptively adjust the support radii to have different parts of the medial surface contracted adaptively and synchronously for generating connected skeletal curves. In this paper, we demonstrate that our method allows for each part of the medial surface to be contracted symmetrically to its center line and is insensitive to surface noises. Thus, with our method, centered and connected high quality curve skeletons can be extracted robustly and rapidly, even for models with nearby surface sheets. Experimental results highlight the effectiveness and high efficiency of the method, even for noisy and topologically complex models, making it superior to other state-of-the-art methods.

Browse

Browsing 37-Issue 7 by Title

Results Per Page

Sort Options