ACM Transactions on Graphics

Journal Information
ISSN / EISSN : 0730-0301 / 1557-7368
Total articles ≅ 4,808
Current Coverage
SCOPUS
SCIE
COMPENDEX
Archived in
SHERPA/ROMEO
Filter:

Latest articles in this journal

Bolun Wang, Zachary Ferguson, Teseo Schneider, Xin Jiang, Marco Attene, Daniele Panozzo
ACM Transactions on Graphics, Volume 40, pp 1-16; https://doi.org/10.1145/3460775

Abstract:
We introduce a large-scale benchmark for continuous collision detection (CCD) algorithms, composed of queries manually constructed to highlight challenging degenerate cases and automatically generated using existing simulators to cover common cases. We use the benchmark to evaluate the accuracy, correctness, and efficiency of state-of-the-art continuous collision detection algorithms, both with and without minimal separation. We discover that, despite the widespread use of CCD algorithms, existing algorithms are (1) correct but impractically slow; (2) efficient but incorrect, introducing false negatives that will lead to interpenetration; or (3) correct but over conservative, reporting a large number of false positives that might lead to inaccuracies when integrated in a simulator. By combining the seminal interval root finding algorithm introduced by Snyder in 1992 with modern predicate design techniques, we propose a simple and efficient CCD algorithm. This algorithm is competitive with state-of-the-art methods in terms of runtime while conservatively reporting the time of impact and allowing explicit tradeoff between runtime efficiency and number of false positives reported.
Andreas Bærentzen, Eva Rotenberg
ACM Transactions on Graphics, Volume 40, pp 1-18; https://doi.org/10.1145/3459233

Abstract:
We propose a new algorithm for curve skeleton computation that differs from previous algorithms by being based on the notion of local separators . The main benefits of this approach are that it is able to capture relatively fine details and that it works robustly on a range of shape representations. Specifically, our method works on shape representations that can be construed as spatially embedded graphs. Such representations include meshes, volumetric shapes, and graphs computed from point clouds. We describe a simple pipeline where geometric data are initially converted to a graph, optionally simplified, local separators are computed and selected, and finally a skeleton is constructed. We test our pipeline on polygonal meshes, volumetric shapes, and point clouds. Finally, we compare our results to other methods for skeletonization according to performance and quality.
Julien Philip, Sébastien Morgenthaler, Michaël Gharbi, George Drettakis
ACM Transactions on Graphics, Volume 40, pp 1-18; https://doi.org/10.1145/3469842

Abstract:
We introduce a neural relighting algorithm for captured indoors scenes, that allows interactive free-viewpoint navigation. Our method allows illumination to be changed synthetically, while coherently rendering cast shadows and complex glossy materials. We start with multiple images of the scene and a three-dimensional mesh obtained by multi-view stereo (MVS) reconstruction. We assume that lighting is well explained as the sum of a view-independent diffuse component and a view-dependent glossy term concentrated around the mirror reflection direction. We design a convolutional network around input feature maps that facilitate learning of an implicit representation of scene materials and illumination, enabling both relighting and free-viewpoint navigation. We generate these input maps by exploiting the best elements of both image-based and physically based rendering. We sample the input views to estimate diffuse scene irradiance, and compute the new illumination caused by user-specified light sources using path tracing. To facilitate the network's understanding of materials and synthesize plausible glossy reflections, we reproject the views and compute mirror images . We train the network on a synthetic dataset where each scene is also reconstructed with MVS. We show results of our algorithm relighting real indoor scenes and performing free-viewpoint navigation with complex and realistic glossy reflections, which so far remained out of reach for view-synthesis techniques.
Gal Metzer, Rana Hanocka, Raja Giryes, Daniel Cohen-Or
ACM Transactions on Graphics, Volume 40, pp 1-14; https://doi.org/10.1145/3470645

Abstract:
We introduce a novel technique for neural point cloud consolidation which learns from only the input point cloud. Unlike other point up-sampling methods which analyze shapes via local patches, in this work, we learn from global subsets. We repeatedly self-sample the input point cloud with global subsets that are used to train a deep neural network. Specifically, we define source and target subsets according to the desired consolidation criteria (e.g., generating sharp points or points in sparse regions). The network learns a mapping from source to target subsets, and implicitly learns to consolidate the point cloud. During inference, the network is fed with random subsets of points from the input, which it displaces to synthesize a consolidated point set. We leverage the inductive bias of neural networks to eliminate noise and outliers, a notoriously difficult problem in point cloud consolidation. The shared weights of the network are optimized over the entire shape, learning non-local statistics and exploiting the recurrence of local-scale geometries. Specifically, the network encodes the distribution of the underlying shape surface within a fixed set of local kernels, which results in the best explanation of the underlying shape surface. We demonstrate the ability to consolidate point sets from a variety of shapes, while eliminating outliers and noise.
Shiqi Chen, Huajun Feng, Dexin Pan, Zhihai Xu, Qi Li, Yueting Chen
ACM Transactions on Graphics, Volume 40, pp 1-15; https://doi.org/10.1145/3474088

Abstract:
As the popularity of mobile photography continues to grow, considerable effort is being invested in the reconstruction of degraded images. Due to the spatial variation in optical aberrations, which cannot be avoided during the lens design process, recent commercial cameras have shifted some of these correction tasks from optical design to postprocessing systems. However, without engaging with the optical parameters, these systems only achieve limited correction for aberrations. In this work, we propose a practical method for recovering the degradation caused by optical aberrations. Specifically, we establish an imaging simulation system based on our proposed optical point spread function model. Given the optical parameters of the camera, it generates the imaging results of these specific devices. To perform the restoration, we design a spatial-adaptive network model on synthetic data pairs generated by the imaging simulation system, eliminating the overhead of capturing training data by a large amount of shooting and registration. Moreover, we comprehensively evaluate the proposed method in simulations and experimentally with a customized digital-single-lens-reflex camera lens and HUAWEI HONOR 20, respectively. The experiments demonstrate that our solution successfully removes spatially variant blur and color dispersion. When compared with the state-of-the-art deblur methods, the proposed approach achieves better results with a lower computational overhead. Moreover, the reconstruction technique does not introduce artificial texture and is convenient to transfer to current commercial cameras. Project Page: https://github.com/TanGeeGo/ImagingSimulation .
Ran Zhang, Thomas Auzinger,
ACM Transactions on Graphics, Volume 40, pp 1-16; https://doi.org/10.1145/3453477

Abstract:
This article presents a method for designing planar multistable compliant structures. Given a sequence of desired stable states and the corresponding poses of the structure, we identify the topology and geometric realization of a mechanism—consisting of bars and joints—that is able to physically reproduce the desired multistable behavior. In order to solve this problem efficiently, we build on insights from minimally rigid graph theory to identify simple but effective topologies for the mechanism. We then optimize its geometric parameters, such as joint positions and bar lengths, to obtain correct transitions between the given poses. Simultaneously, we ensure adequate stability of each pose based on an effective approximate error metric related to the elastic energy Hessian of the bars in the mechanism. As demonstrated by our results, we obtain functional multistable mechanisms of manageable complexity that can be fabricated using 3D printing. Further, we evaluated the effectiveness of our method on a large number of examples in the simulation and fabricated several physical prototypes.
Zhi-Chao Dong, Wenming Wu, Zenghao Xu, Qi Sun, Guanjie Yuan, Ligang Liu, Xiao-Ming Fu
ACM Transactions on Graphics, Volume 40, pp 1-15; https://doi.org/10.1145/3470847

Abstract:
In virtual reality (VR), the virtual scenes are pre-designed by creators. Our physical surroundings, however, comprise significantly varied sizes, layouts, and components. To bridge the gap and further enable natural navigation, recent solutions have been proposed to redirect users or recreate the virtual content. However, they suffer from either interrupted experience or distorted appearances. We present a novel VR-oriented algorithm that automatically restructures a given virtual scene for a user’s physical environment. Different from the previous methods, we introduce neither interrupted walking experience nor curved appearances. Instead, a perception-aware function optimizes our retargeting technique to preserve the fidelity of the virtual scene that appears in VR head-mounted displays. Besides geometric and topological properties, it emphasizes the unique first-person view perceptual factors in VR, such as dynamic visibility and objectwise relationships. We conduct both analytical experiments and subjective studies. The results demonstrate our system’s versatile capability and practicability for natural navigation in VR: It reduces the virtual space by 40% without statistical loss of perceptual identicality.
Michael Mara, Felix Heide, Michael Zollhöfer, Matthias Nießner, Pat Hanrahan
ACM Transactions on Graphics, Volume 40, pp 1-14; https://doi.org/10.1145/3453986

Abstract:
Large-scale optimization problems at the core of many graphics, vision, and imaging applications are often implemented by hand in tedious and error-prone processes in order to achieve high performance (in particular on GPUs), despite recent developments in libraries and DSLs. At the same time, these hand-crafted solver implementations reveal that the key for high performance is a problem-specific schedule that enables efficient usage of the underlying hardware. In this work, we incorporate this insight into Thallo, a domain-specific language for large-scale non-linear least squares optimization problems. We observe various code reorganizations performed by implementers of high-performance solvers in the literature, and then define a set of basic operations that span these scheduling choices, thereby defining a large scheduling space. Users can either specify code transformations in a scheduling language or use an autoscheduler. Thallo takes as input a compact, shader-like representation of an energy function and a (potentially auto-generated) schedule, translating the combination into high-performance GPU solvers. Since Thallo can generate solvers from a large scheduling space, it can handle a large set of large-scale non-linear and non-smooth problems with various degrees of non-locality and compute-to-memory ratios, including diverse applications such as bundle adjustment, face blendshape fitting, and spatially-varying Poisson deconvolution, as seen in Figure 1. Abstracting schedules from the optimization, we outperform state-of-the-art GPU-based optimization DSLs by an average of 16× across all applications introduced in this work, and even some published hand-written GPU solvers by 30%+.
Lohit Petikam, Ken Anjyo, Taehyun Rhee
ACM Transactions on Graphics, Volume 40, pp 1-14; https://doi.org/10.1145/3461696

Abstract:
Despite the popularity of three-dimensional (3D) animation techniques, the style of 2D cel animation is seeing increased use in games and interactive applications. However, conventional 3D toon shading frequently requires manual editing to clean up undesired shadows or add stylistic details based on art direction. This editing is impractical for the frame-by-frame editing in cartoon feature film post-production. For interactive stylised media and games, post-production is unavailable due to real-time constraints, so art-direction must be preserved automatically. For these reasons, artists often resort to mesh and texture edits to mitigate undesired shadows typical of toon shaders. Such edits allow real-time rendering but are limited in resolution, animation quality and lack detail control for stylised shadow design. In our framework, artists build a “shading rig,” a collection of these edits, that allows artists to animate toon shading. Artists pre-animate the shading rig under changing lighting, to dynamically preserve artistic intent in a live application, without manual intervention. We show our method preserves continuous motion and shape interpolation, with fewer keyframes than previous work. Our shading shape interpolation is computationally cheaper than state-of-the-art image interpolation techniques. We achieve these improvements while preserving vector quality rendering, without resorting either to high texture resolution or mesh density.
Hyeongseok Son, Junyong Lee, Jonghyeop Lee, Sunghyun Cho, Seungyong Lee
ACM Transactions on Graphics, Volume 40, pp 1-18; https://doi.org/10.1145/3453720

Abstract:
For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames that can help deblur a target frame. However, the motion compensation methods adopted by previous deblurring methods are not blur-invariant, and consequently, their accuracy is limited for blurry frames with different blur amounts. To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multiple video frames. First, we present blur-invariant motion estimation learning to improve motion estimation accuracy between blurry frames. Second, for motion compensation, instead of aligning frames by warping with estimated motions, we use a pixel volume that contains candidate sharp pixels to resolve motion estimation errors. We combine these two processes to propose an effective recurrent video deblurring network that fully exploits deblurred previous frames. Experiments show that our method achieves the state-of-the-art performance both quantitatively and qualitatively compared to recent methods that use deep learning.
Back to Top Top