Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 46
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Artigo em Inglês | MEDLINE | ID: mdl-32011257

RESUMO

We present prominent structures in video, a representation of visually strong, spatially sparse and temporally stable structural units, for use in video analysis and editing. With a novel quality measurement of prominent structures in video, we develop a general framework for prominent structure computation, and an efficient hierarchical structure alignment algorithm between a pair of videos. The prominent structural unit map is proposed to encode both binary prominence guidance and numerical strength and geometry details for each video frame. Even though the detailed appearance of videos could be visually different, the proposed alignment algorithm can find matched prominent structure sub-volumes. Prominent structures in video support a wide range of video analysis and editing applications including graphic match-cut between successive videos, instant cut editing, finding transition portals from a video collection, structure-aware video re-ranking, visualizing human action differences, etc.

2.
IEEE Trans Vis Comput Graph ; 26(2): 1361-1371, 2020 Feb.
Artigo em Inglês | MEDLINE | ID: mdl-30176598

RESUMO

This paper presents Poisson vector graphics (PVG), an extension of the popular diffusion curves (DC), for generating smooth-shaded images. Armed with two new types of primitives, called Poisson curves and Poisson regions, PVG can easily produce photorealistic effects such as specular highlights, core shadows, translucency and halos. Within the PVG framework, the users specify color as the Dirichlet boundary condition of diffusion curves and control tone by offsetting the Laplacian of colors, where both controls are simply done by mouse click and slider dragging. PVG distinguishes itself from other diffusion based vector graphics for 3 unique features: 1) explicit separation of colors and tones, which follows the basic drawing principle and eases editing; 2) native support of seamless cloning in the sense that PCs and PRs can automatically fit into the target background; and 3) allowed intersecting primitives (except for DC-DC intersection) so that users can create layers. Through extensive experiments and a preliminary user study, we demonstrate that PVG is a simple yet powerful authoring tool that can produce photo-realistic vector graphics from scratch.

3.
Artigo em Inglês | MEDLINE | ID: mdl-31796407

RESUMO

We propose an objective approach to assess the quality of video blending. Blending is a fundamental operation in video editing, which can smooth the intensity changes of relevant regions. However blending also generates artefacts such as bleeding and ghosting. To assess the quality of the blended videos, our approach considers the illuminance consistency as a positive aspect while regard the artefacts as a negative aspect. Temporal coherence between frames is also considered. We evaluate our metric on a video blending dataset where the results of subjective evaluation are available. Experimental results validate the effectiveness of our proposed metric, and shows that this metric gives superior performance over existing video quality metrics.

4.
Artigo em Inglês | MEDLINE | ID: mdl-31613764

RESUMO

General image completion and extrapolation methods often fail on portrait images where parts of the human body need to be recovered -a task that requires accurate human body structure and appearance synthesis. We present a twostage deep learning framework for tackling this problem. In the first stage, given a portrait image with an incomplete human body, we extract a complete, coherent human body structure through a human parsing network, which focuses on structure recovery inside the unknown region with the help of full-body pose estimation. In the second stage, we use an image completion network to fill the unknown region, guided by the structure map recovered in the first stage. For realistic synthesis the completion network is trained with both perceptual loss and conditional adversarial loss.We further propose a face refinement network to improve the fidelity of the synthesized face region. We evaluate our method on publicly-available portrait image datasets, and show that it outperforms other state-of-the-art general image completion methods. Our method enables new portrait image editing applications such as occlusion removal and portrait extrapolation. We further show that the proposed general learning framework can be applied to other types of images, e.g. animal images.

5.
Diabetes Metab Syndr Obes ; 12: 983-989, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31417298

RESUMO

Background: Four novel glucose metabolism risk loci (HKDC1 rs4746822, BACE2 rs6517656, SLC16A11 rs13342232 and TMEM163 rs998451) were identified in recent genome-wide association studies (GWAS) of Afro-Caribbean, European, Hispanic, Thai, Mexican, Latin American and Indian populations. None of the abovementioned SNPs has been reported in a Han Chinese population. Aim: To replicate the relationships between HKDC1 rs4746822, BACE2 rs6517656, SLC16A11 rs13342232 and TMEM163 rs998451 with gestational diabetes mellitus (GDM) in a Han Chinese population. Methods: This was a case-control study which enrolled 334 pregnant women with GDM and 367 pregnant women with normal glucose tolerance. The linear regression and logistic regression were used to estimate the association between SNPs with the risk of GDM, HOMA-IR and fasting insulin levels. The fasting insulin concentration and HOMA-IR were log10 transformed before analysis. Results: No significant differences in the alleles and genotypes of SLC16A11 rs13342232, HKDC1 rs4746822 and BACE2 rs6517656 were observed between cases and controls. After adjusting the weekly BMI growth, pre-pregnancy BMI and maternal age, under the additive model, SLC16A11 rs13342232 was associated with log10fasting serum insulin (Beta=0.046, p=0.016), log10HOMA-IR level (Beta=0.061, p=0.003) and fasting plasma glucose level (Beta=0.164, p=0.011); HKDC1 rs4746822 was associated with OGTT 2-hr plasma glucose level (Beta=0.239, p=0.016); and BACE2 rs6517656 was associated with log10fasting serum insulin (Beta=-0.053, p=0.044) and log10HOMA-IR level (Beta=-0.060, p=0.048). After correction for multiple testing, the associations of SLC16A11 and HKDC1 with glucose metabolism remained statistically significant. The A allele of TMEM163 rs998451 was not detected in this population. Conclusion: HKDC1 rs4746822, BACE2 rs6517656 and SLC16A11 rs13342232 are associated with glucose metabolism in pregnant women of Han Chinese.

6.
Artigo em Inglês | MEDLINE | ID: mdl-31449026

RESUMO

We present a learning-based approach to reconstructing high-resolution three-dimensional (3D) shapes with detailed geometry and high-fidelity textures. Albeit extensively studied, algorithms for 3D reconstruction from multi-view depth-and-color (RGB-D) scans are still prone to measurement noise and occlusions; limited scanning or capturing angles also often lead to incomplete reconstructions. Propelled by recent advances in 3D deep learning techniques, in this paper, we introduce a novel computation and memory efficient cascaded 3D convolutional network architecture, which learns to reconstruct implicit surface representations as well as the corresponding color information from noisy and imperfect RGB-D maps. The proposed 3D neural network performs reconstruction in a progressive and coarse-to-fine manner, achieving unprecedented output resolution and fidelity. Meanwhile, an algorithm for end-to-end training of the proposed cascaded structure is developed. We further introduce Human10, a newly created dataset containing both detailed and textured full body reconstructions as well as corresponding raw RGB-D scans of 10 subjects. Qualitative and quantitative experimental results on both synthetic and real-world datasets demonstrate that the presented approach outperforms existing state-of-the-art work in terms of visual quality and accuracy of reconstructed models.

7.
Artigo em Inglês | MEDLINE | ID: mdl-31150341

RESUMO

We present a real-time approach that integrates multiple sensors for dense reconstruction of 3D indoor scenes. Existing algorithms are mainly based on a single RGBD camera and require continuous scanning on areas with sufficient geometric details. Failing to do so can lead to tracking loss due to the lack of frame registration hints. Inspired by the fact that utilizing multiple sensors can combine their strengths to form a more robust and accurate implementation, we incorporate multiple types of sensors, which are prevalently equipped in modern robots, including a 2D range sensor, an IMU, and wheel encoders to reinforce the tracking process and obtain better mesh construction. Specifically, we develop a feasible 2D TSDF volume representation for integrating and ray-casting laser frames, leading to a unified cost function in the pose estimation stage. Besides, for validating these estimated poses in the loop-closure optimization process, we train a classifier according to those features extracted from heterogeneous sensors and the registration progress. To evaluate our method on challenging robotic scanning scenarios, we assembled a scanning platform for acquiring real-world scans. We further simulated synthetic scans based on high-fidelity synthetic scenes for quantitative evaluation. Extensive experimental results demonstrate that our system is capable of robustly acquiring dense reconstructions and outperforms state-of-the-art systems.

8.
IEEE Trans Image Process ; 28(9): 4413-4428, 2019 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-31071029

RESUMO

A quick-response code (QR code) is a two-dimensional code akin to a barcode that encodes a message of limited length. In this paper, we present a variant of QR code, a two-layer QR code. Its two-layer structure can display two alternative messages when scanned from two different directions. We propose a method to generate such two-layer QR codes encoding two given messages in a few seconds. We also demonstrate the robustness of our method on both synthetic and fabricated examples. All source code will be made publicly available (https://github.com/yuantailing/two-layer-qrcode).

9.
World J Clin Cases ; 7(5): 585-599, 2019 Mar 06.
Artigo em Inglês | MEDLINE | ID: mdl-30863758

RESUMO

BACKGROUND: Resistin is most likely involved in the pathogenesis of gestational diabetes mellitus (GDM), but the existing findings are inconsistent. AIM: To review the literature investigating the associations of the risk of GDM with serum level of resistin. METHODS: A systematic literature search was performed using MEDLINE, EMBASE, and Web of Science (all databases). This meta-analysis included eligible studies that: (1) investigated the relationship between the risk of GDM and serum resistin; (2) included GDM cases and controls without GDM; (3) diagnosed GDM according to the oral glucose-tolerance test; (4) were performed in humans; (5) were published as full text articles in English; and (6) provided data with median and quartile range, median and minimum and maximum values, or mean and standard deviation. The pooled standardized mean difference (SMD) and 95% confidence interval (CI) were calculated to estimate the association between the risk of GDM and serum resistin. To analyze the potential influences of need for insulin in GDM patients and gestational age at blood sampling, we performed a subgroup analysis. Meta-regression with restricted maximum likelihood estimation was performed to assess the potentially important covariate exerting substantial impact on between-study heterogeneity. RESULTS: The meta-analysis for the association between serum resistin level and GDM risk included 18 studies (22 comparisons) with 1041 cases and 1292 controls. The total results showed that the risk of GDM was associated with higher serum resistin level (SMD = 0.250, 95%CI: 0.116, 0.384). The "after 28 wk" subgroup, "no need for insulin" subgroup, and "need for insulin" subgroup indicated that higher serum resistin level was related to GDM risk ("after 28 wk" subgroup: SMD = 0.394, 95%CI: 0.108, 0.680; "no need for insulin" subgroup: SMD = 0.177, 95%CI: 0.018, 0.336; "need for insulin" subgroup: SMD = 0.403, 95%CI: 0.119, 0.687). The "before 14 wk" subgroup, "14-28 wk" subgroup, and "no information of need for insulin" subgroup showed a nonsignificant association between serum resistin level and GDM risk ("before 14 wk" subgroup: SMD = 0.087, 95%CI: -0.055, 0.230; "14-28 wk" subgroup: SMD = 0.217, 95%CI: -0.003, 0.436; "no information of need for insulin" subgroup: SMD = 0.356, 95%CI: -0.143, 0.855). The postpartum subgroup included only one study and showed that higher serum resistin level was related to GDM risk (SMD = 0.571, 95%CI: 0.054, 1.087) The meta-regression revealed that no need for insulin in GDM patients, age distribution similar between cases and controls, and ELISA all had a significant impact on between-study heterogeneity. CONCLUSION: This meta-analysis supports that the maternal serum resistin level is associated with GDM risk.

10.
Artigo em Inglês | MEDLINE | ID: mdl-30507533

RESUMO

Video stabilization techniques are essential for most hand-held captured videos due to high-frequency shakes. Several 2D, 2.5D and 3D-based stabilization techniques have been presented previously, but to our knowledge, no solutions based on deep neural networks had been proposed to date. The main reason for this omission is shortage in training data as well as the challenge of modeling the problem using neural networks. In this paper, we present a video stabilization technique using a convolutional neural network. Previous works usually propose an offline algorithm that smoothes a holistic camera path based on feature matching. Instead, we focus on low-latency, real-time camera path smoothing, that does not explicitly represent the camera path, and does not use future frames. Our neural network model, called StabNet, learns a set of mesh-grid transformations progressively for each input frame from the previous set of stabalized camera frames, and creates stable corresponding latent camera paths implicitly. To train the network, we collect a dataset of synchronized steady and unsteady video pairs via a specially designed hand-held hardware. Experimental results show that our proposed online method performs comparatively to traditional offline video stabilization methods without using future frames, while running about 10× faster. More importantly, our proposed StabNet is able to handle low-quality videos such as night-scene videos, watermarked videos, blurry videos and noisy videos, where existing methods fail in feature extraction or matching.

11.
IEEE Trans Vis Comput Graph ; 24(10): 2728-2742, 2018 10.
Artigo em Inglês | MEDLINE | ID: mdl-29990001

RESUMO

We present a visual analysis method for interactively recomposing a large number of photos based on example photos with high-quality composition. The recomposition method is formulated as a matching problem between photos. The key to this formulation is a new metric for accurately measuring the composition distance between photos. We have also developed an earth-mover-distance-based online metric learning algorithm to support the interactive adjustment of the composition distance based on user preferences. To better convey the compositions of a large number of example photos, we have developed a multi-level, example photo layout method to balance multiple factors such as compactness, aspect ratio, composition distance, stability, and overlaps. By introducing an EulerSmooth-based straightening method, the composition of each photos is clearly displayed. The effectiveness and usefulness of the method has been demonstrated by the experimental results, user study, and case studies.

12.
IEEE Trans Image Process ; 27(12): 5854-5865, 2018 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-30047880

RESUMO

Selfie photography from the hand-held camera is becoming a popular media type. Although being convenient and flexible, it suffers from low camera motion stability, small field of view, and limited background content. These limitations can annoy users, especially, when touring a place of interest and taking selfie videos. In this paper, we present a novel method to create what we call a BiggerSelfie that deals with these shortcomings. Using a video of the environment that has partial content overlap with the selfie video, we stitch plausible frames selected from the environment video to the original selfie frames and stabilize the composed video content with a portrait-preserving constraint. Using the proposed method, one can easily obtain a stable selfie video with expanded background content by merely capturing some background shots. We show various results and several evaluations to demonstrate the applicability of our method.

13.
IEEE Trans Image Process ; 27(6): 2952-2965, 2018 06.
Artigo em Inglês | MEDLINE | ID: mdl-29993600

RESUMO

Unlike image blending algorithms, video blending algorithms have been little studied. In this paper, we investigate 6 popular blending algorithms-feather blending, multi-band blending, modified Poisson blending, mean value coordinate blending, multi-spline blending and convolution pyramid blending. We consider their application to blending realtime panoramic videos, a key problem in various virtual reality tasks. To evaluate the performances and suitabilities of the 6 algorithms for this problem, we have created a video benchmark with several videos captured under various conditions. We analyze the time and memory needed by the above 6 algorithms, for both CPU and GPU implementations (where readily parallelizable). The visual quality provided by these algorithms is also evaluated both objectively and subjectively. The video benchmark and algorithm implementations are publicly available1.

14.
IEEE Trans Image Process ; 27(4): 1735-1747, 2018 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-28880175

RESUMO

Hyper-lapse video with high speed-up rate is an efficient way to overview long videos, such as a human activity in first-person view. Existing hyper-lapse video creation methods produce a fast-forward video effect using only one video source. In this paper, we present a novel hyper-lapse video creation approach based on multiple spatially-overlapping videos. We assume the videos share a common view or location, and find transition points where jumps from one video to another may occur. We represent the collection of videos using a hyper-lapse transition graph; the edges between nodes represent possible hyper-lapse frame transitions. To create a hyper-lapse video, a shortest path search is performed on this digraph to optimize frame sampling and assembly simultaneously. Finally, we render the hyper-lapse results using video stabilization and appearance smoothing techniques on the selected frames. Our technique can synthesize novel virtual hyper-lapse routes, which may not exist originally. We show various application results on both indoor and outdoor video collections with static scenes, moving objects, and crowds.

15.
IEEE Trans Vis Comput Graph ; 24(8): 2411-2423, 2018 08.
Artigo em Inglês | MEDLINE | ID: mdl-28682258

RESUMO

Surface flow phenomena, such as rain water flowing down a tree trunk and progressive water front in a shower room, are common in real life. However, compared with the 3D spatial fluid flow, these surface flow problems have been much less studied in the graphics community. To tackle this research gap, we present an efficient, robust and high-fidelity simulation approach based on the shallow-water equations. Specifically, the standard shallow-water flow model is extended to general triangle meshes with a feature-based bottom friction model, and a series of coherent mathematical formulations are derived to represent the full range of physical effects that are important for real-world surface flow phenomena. In addition, by achieving compatibility with existing 3D fluid simulators and by supporting physically realistic interactions with multiple fluids and solid surfaces, the new model is flexible and readily extensible for coupled phenomena. A wide range of simulation examples are presented to demonstrate the performance of the new approach.

16.
Artigo em Inglês | MEDLINE | ID: mdl-30596579

RESUMO

We present a novel algorithm for semantic segmentation and labeling of 3D point clouds of indoor scenes, where objects in point clouds can have significant variations and complex configurations. Effective segmentation methods decomposing point clouds into semantically meaningful pieces are highly desirable for object recognition, scene understanding, scene modeling, etc. However, existing segmentation methods based on low-level geometry tend to either under-segment or over-segment point clouds. Our method takes a fundamentally different approach, where semantic segmentation is achieved along with labeling. To cope with substantial shape variation for objects in the same category, we first segment point clouds into surface patches and use unsupervised clustering to group patches in the training set into clusters, providing an intermediate representation for effectively learning patch relationships. During testing, we propose a novel patch segmentation and classification framework with multiscale processing, where the local segmentation level is automatically determined by exploiting the learned cluster based contextual information. Our method thus produces robust patch segmentation and semantic labeling results, avoiding parameter sensitivity. We further learn object-cluster relationships from the training set, and produce semantically meaningful object level segmentation.Our method outperforms state-of-the-art methods on several representative point cloud datasets, including S3DIS, SceneNN, Cornell RGB-D and ETH.

17.
IEEE Trans Vis Comput Graph ; 23(10): 2235-2247, 2017 10.
Artigo em Inglês | MEDLINE | ID: mdl-28541209

RESUMO

In this paper, we present a novel pairwise-force smoothed particle hydrodynamics (PF-SPH) model to enable simulation of various interactions at interfaces in real time. Realistic capture of interactions at interfaces is a challenging problem for SPH-based simulations, especially for scenarios involving multiple interactions at different interfaces. Our PF-SPH model can readily handle multiple types of interactions simultaneously in a single simulation; its basis is to use a larger support radius than that used in standard SPH. We adopt a novel anisotropic filtering term to further improve the performance of interaction forces. The proposed model is stable; furthermore, it avoids the particle clustering problem which commonly occurs at the free surface. We show how our model can be used to capture various interactions. We also consider the close connection between droplets and bubbles, and show how to animate bubbles rising in liquid as well as bubbles in air. Our method is versatile, physically plausible and easy-to-implement. Examples are provided to demonstrate the capabilities and effectiveness of our approach.

18.
IEEE Trans Vis Comput Graph ; 23(5): 1561-1573, 2017 05.
Artigo em Inglês | MEDLINE | ID: mdl-26915124

RESUMO

Patch-based image synthesis methods have been successfully applied for various editing tasks on still images, videos and stereo pairs. In this work we extend patch-based synthesis to plenoptic images captured by consumer-level lenselet-based devices for interactive, efficient light field editing. In our method the light field is represented as a set of images captured from different viewpoints. We decompose the central view into different depth layers, and present it to the user for specifying the editing goals. Given an editing task, our method performs patch-based image synthesis on all affected layers of the central view, and then propagates the edits to all other views. Interaction is done through a conventional 2D image editing user interface that is familiar to novice users. Our method correctly handles object boundary occlusion with semi-transparency, thus can generate more realistic results than previous methods. We demonstrate compelling results on a wide range of applications such as hole-filling, object reshuffling and resizing, changing object depth, light field upscaling and parallax magnification.

19.
IEEE Trans Image Process ; 25(3): 1152-62, 2016 Mar.
Artigo em Inglês | MEDLINE | ID: mdl-26731765

RESUMO

In this paper, we present a novel algorithm to simultaneously accomplish color quantization and dithering of images. This is achieved by minimizing a perception-based cost function, which considers pixel-wise differences between filtered versions of the quantized image and the input image. We use edge aware filters in defining the cost function to avoid mixing colors on the opposite sides of an edge. The importance of each pixel is weighted according to its saliency. To rapidly minimize the cost function, we use a modified multi-scale iterative conditional mode (ICM) algorithm, which updates one pixel a time while keeping other pixels unchanged. As ICM is a local method, careful initialization is required to prevent termination at a local minimum far from the global one. To address this problem, we initialize ICM with a palette generated by a modified median-cut method. Compared with previous approaches, our method can produce high-quality results with a fewer visual artifacts but also requires significantly less computational effort.

20.
IEEE Trans Vis Comput Graph ; 22(8): 2024-36, 2016 08.
Artigo em Inglês | MEDLINE | ID: mdl-26336128

RESUMO

In this work we explore a support-induced structural organization of object parts. We introduce the concept of support substructures, which are special subsets of object parts with support and stability. A bottom-up approach is proposed to identify such substructures in a support relation graph. We apply the derived high-level substructures to part-based shape reshuffling between models, resulting in nontrivial functionally plausible model variations that are difficult to achieve with symmetry-induced substructures by the state-of-the-art methods. We also show how to automatically or interactively turn a single input model to new functionally plausible shapes by structure rearrangement and synthesis, enabled by support substructures. To the best of our knowledge no single existing method has been designed for all these applications.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA