In this paper we propose a noval method to generate the specified network parameters through one feed-forward propagation in the meta networks for neural style transfer. Recent works on style transfer typically need to train image transformation networks for every new style, and the style is encoded in the network parameters by enormous iterations of stochastic gradient descent, which lacks the generalization ability to new style in the inference stage. To tackle these issues, we build a meta network which takes in the style image and generates a corresponding image transformation network directly. Compared with optimization-based methods for every style, our meta networks can handle an arbitrary new style within 19 milliseconds on one modern GPU card. The fast image transformation network generated by our meta network is only 449 KB, which is capable of real-time running on a mobile device. We also investigate the manifold of the style transfer networks by operating the hidden features from meta networks. Experiments have well validated the effectiveness of our method. Code and trained models will be released.
{"title":"Neural Style Transfer via Meta Networks","authors":"Falong Shen, Shuicheng Yan, Gang Zeng","doi":"10.1109/CVPR.2018.00841","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00841","url":null,"abstract":"In this paper we propose a noval method to generate the specified network parameters through one feed-forward propagation in the meta networks for neural style transfer. Recent works on style transfer typically need to train image transformation networks for every new style, and the style is encoded in the network parameters by enormous iterations of stochastic gradient descent, which lacks the generalization ability to new style in the inference stage. To tackle these issues, we build a meta network which takes in the style image and generates a corresponding image transformation network directly. Compared with optimization-based methods for every style, our meta networks can handle an arbitrary new style within 19 milliseconds on one modern GPU card. The fast image transformation network generated by our meta network is only 449 KB, which is capable of real-time running on a mobile device. We also investigate the manifold of the style transfer networks by operating the hidden features from meta networks. Experiments have well validated the effectiveness of our method. Code and trained models will be released.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"13 1","pages":"8061-8069"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82966829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is more robust to occlusion as well as sparse data at range. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world, which is very efficient in terms of both memory and computation. Our experiments on a new very large scale dataset captured in several north american cities, show that we can outperform the state-of-the-art by a large margin. Importantly, by sharing computation we can perform all tasks in as little as 30 ms.
{"title":"Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net","authors":"Wenjie Luo, Binh Yang, R. Urtasun","doi":"10.1109/CVPR.2018.00376","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00376","url":null,"abstract":"In this paper we propose a novel deep neural network that is able to jointly reason about 3D detection, tracking and motion forecasting given data captured by a 3D sensor. By jointly reasoning about these tasks, our holistic approach is more robust to occlusion as well as sparse data at range. Our approach performs 3D convolutions across space and time over a bird's eye view representation of the 3D world, which is very efficient in terms of both memory and computation. Our experiments on a new very large scale dataset captured in several north american cities, show that we can outperform the state-of-the-art by a large margin. Importantly, by sharing computation we can perform all tasks in as little as 30 ms.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"40 1","pages":"3569-3577"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78450607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Domain adaptation attempts to transfer the knowledge obtained from the source domain to the target domain, i.e., the domain where the testing data are. The main challenge lies in the distribution discrepancy between source and target domain. Most existing works endeavor to learn domain invariant representation usually by minimizing a distribution distance, e.g., MMD and the discriminator in the recently proposed generative adversarial network (GAN). Following the similar idea of GAN, this work proposes a novel GAN architecture with duplex adversarial discriminators (referred to as DupGAN), which can achieve domain-invariant representation and domain transformation. Specifically, our proposed network consists of three parts, an encoder, a generator and two discriminators. The encoder embeds samples from both domains into the latent representation, and the generator decodes the latent representation to both source and target domains respectively conditioned on a domain code, i.e., achieves domain transformation. The generator is pitted against duplex discriminators, one for source domain and the other for target, to ensure the reality of domain transformation, the latent representation domain invariant and the category information of it preserved as well. Our proposed work achieves the state-of-the-art performance on unsupervised domain adaptation of digit classification and object recognition.
{"title":"Duplex Generative Adversarial Network for Unsupervised Domain Adaptation","authors":"Lanqing Hu, Meina Kan, S. Shan, Xilin Chen","doi":"10.1109/CVPR.2018.00162","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00162","url":null,"abstract":"Domain adaptation attempts to transfer the knowledge obtained from the source domain to the target domain, i.e., the domain where the testing data are. The main challenge lies in the distribution discrepancy between source and target domain. Most existing works endeavor to learn domain invariant representation usually by minimizing a distribution distance, e.g., MMD and the discriminator in the recently proposed generative adversarial network (GAN). Following the similar idea of GAN, this work proposes a novel GAN architecture with duplex adversarial discriminators (referred to as DupGAN), which can achieve domain-invariant representation and domain transformation. Specifically, our proposed network consists of three parts, an encoder, a generator and two discriminators. The encoder embeds samples from both domains into the latent representation, and the generator decodes the latent representation to both source and target domains respectively conditioned on a domain code, i.e., achieves domain transformation. The generator is pitted against duplex discriminators, one for source domain and the other for target, to ensure the reality of domain transformation, the latent representation domain invariant and the category information of it preserved as well. Our proposed work achieves the state-of-the-art performance on unsupervised domain adaptation of digit classification and object recognition.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"32 1","pages":"1498-1507"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78544129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Identifying small size images or small objects is a notoriously challenging problem, as discriminative representations are difficult to learn from the limited information contained in them with poor-quality appearance and unclear object structure. Existing research works usually increase the resolution of low-resolution image in the pixel space in order to provide better visual quality for human viewing. However, the improved performance of such methods is usually limited or even trivial in the case of very small image size (we will show it in this paper explicitly). In this paper, different from image super-resolution (ISR), we propose a novel super-resolution technique called feature super-resolution (FSR), which aims at enhancing the discriminatory power of small size image in order to provide high recognition precision for machine. To achieve this goal, we propose a new Feature Super-Resolution Generative Adversarial Network (FSR-GAN) model that transforms the raw poor features of small size images to highly discriminative ones by performing super-resolution in the feature space. Our FSR-GAN consists of two subnetworks: a feature generator network G and a feature discriminator network D. By training the G and the D networks in an alternative manner, we encourage the G network to discover the latent distribution correlations between small size and large size images and then use G to improve the representations of small images. Extensive experiment results on Oxford5K, Paris, Holidays, and Flick100k datasets demonstrate that the proposed FSR approach can effectively enhance the discriminatory ability of features. Even when the resolution of query images is reduced greatly, e.g., 1/64 original size, the query feature enhanced by our FSR approach achieves surprisingly high retrieval performance at different image resolutions and increases the retrieval precision by 25% compared to the raw query feature.
{"title":"Feature Super-Resolution: Make Machine See More Clearly","authors":"Weimin Tan, Bo Yan, Bahetiyaer Bare","doi":"10.1109/CVPR.2018.00420","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00420","url":null,"abstract":"Identifying small size images or small objects is a notoriously challenging problem, as discriminative representations are difficult to learn from the limited information contained in them with poor-quality appearance and unclear object structure. Existing research works usually increase the resolution of low-resolution image in the pixel space in order to provide better visual quality for human viewing. However, the improved performance of such methods is usually limited or even trivial in the case of very small image size (we will show it in this paper explicitly). In this paper, different from image super-resolution (ISR), we propose a novel super-resolution technique called feature super-resolution (FSR), which aims at enhancing the discriminatory power of small size image in order to provide high recognition precision for machine. To achieve this goal, we propose a new Feature Super-Resolution Generative Adversarial Network (FSR-GAN) model that transforms the raw poor features of small size images to highly discriminative ones by performing super-resolution in the feature space. Our FSR-GAN consists of two subnetworks: a feature generator network G and a feature discriminator network D. By training the G and the D networks in an alternative manner, we encourage the G network to discover the latent distribution correlations between small size and large size images and then use G to improve the representations of small images. Extensive experiment results on Oxford5K, Paris, Holidays, and Flick100k datasets demonstrate that the proposed FSR approach can effectively enhance the discriminatory ability of features. Even when the resolution of query images is reduced greatly, e.g., 1/64 original size, the query feature enhanced by our FSR approach achieves surprisingly high retrieval performance at different image resolutions and increases the retrieval precision by 25% compared to the raw query feature.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"143 1","pages":"3994-4002"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78680638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we present an end-to-end multi-level fusion based framework for 3D object detection from a single monocular image. The whole network is composed of two parts: one for 2D region proposal generation and another for simultaneously predictions of objects' 2D locations, orientations, dimensions, and 3D locations. With the help of a stand-alone module to estimate the disparity and compute the 3D point cloud, we introduce the multi-level fusion scheme. First, we encode the disparity information with a front view feature representation and fuse it with the RGB image to enhance the input. Second, features extracted from the original input and the point cloud are combined to boost the object detection. For 3D localization, we introduce an extra stream to predict the location information from point cloud directly and add it to the aforementioned location prediction. The proposed algorithm can directly output both 2D and 3D object detection results in an end-to-end fashion with only a single RGB image as the input. The experimental results on the challenging KITTI benchmark demonstrate that our algorithm significantly outperforms monocular state-of-the-art methods.
{"title":"Multi-level Fusion Based 3D Object Detection from Monocular Images","authors":"Bin Xu, Zhenzhong Chen","doi":"10.1109/CVPR.2018.00249","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00249","url":null,"abstract":"In this paper, we present an end-to-end multi-level fusion based framework for 3D object detection from a single monocular image. The whole network is composed of two parts: one for 2D region proposal generation and another for simultaneously predictions of objects' 2D locations, orientations, dimensions, and 3D locations. With the help of a stand-alone module to estimate the disparity and compute the 3D point cloud, we introduce the multi-level fusion scheme. First, we encode the disparity information with a front view feature representation and fuse it with the RGB image to enhance the input. Second, features extracted from the original input and the point cloud are combined to boost the object detection. For 3D localization, we introduce an extra stream to predict the location information from point cloud directly and add it to the aforementioned location prediction. The proposed algorithm can directly output both 2D and 3D object detection results in an end-to-end fashion with only a single RGB image as the input. The experimental results on the challenging KITTI benchmark demonstrate that our algorithm significantly outperforms monocular state-of-the-art methods.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"30 1","pages":"2345-2353"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84166953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The known rotation problem refers to a special case of structure-from-motion where the absolute orientations of the cameras are known. When formulated as a minimax ($$) problem on reprojection errors, the problem is an instance of pseudo-convex programming. Though theoretically tractable, solving the known rotation problem on large-scale data (1,000's of views, 10,000's scene points) using existing methods can be very time-consuming. In this paper, we devise a fast algorithm for the known rotation problem. Our approach alternates between pose estimation and triangulation (i.e., resection-intersection) to break the problem into multiple simpler instances of pseudo-convex programming. The key to the vastly superior performance of our method lies in using a novel minimum enclosing ball (MEB) technique for the calculation of updating steps, which obviates the need for convex optimisation routines and greatly reduces memory footprint. We demonstrate the practicality of our method on large-scale problem instances which easily overwhelm current state-of-the-art algorithms.
{"title":"A Fast Resection-Intersection Method for the Known Rotation Problem","authors":"Qianggong Zhang, Tat-Jun Chin, Huu Le","doi":"10.1109/CVPR.2018.00318","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00318","url":null,"abstract":"The known rotation problem refers to a special case of structure-from-motion where the absolute orientations of the cameras are known. When formulated as a minimax ($$) problem on reprojection errors, the problem is an instance of pseudo-convex programming. Though theoretically tractable, solving the known rotation problem on large-scale data (1,000's of views, 10,000's scene points) using existing methods can be very time-consuming. In this paper, we devise a fast algorithm for the known rotation problem. Our approach alternates between pose estimation and triangulation (i.e., resection-intersection) to break the problem into multiple simpler instances of pseudo-convex programming. The key to the vastly superior performance of our method lies in using a novel minimum enclosing ball (MEB) technique for the calculation of updating steps, which obviates the need for convex optimisation routines and greatly reduces memory footprint. We demonstrate the practicality of our method on large-scale problem instances which easily overwhelm current state-of-the-art algorithms.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"46 1","pages":"3012-3021"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84141661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dingwen Zhang, Guangyu Guo, Dong Huang, Junwei Han
Motion of the human body is the critical cue for understanding and characterizing human behavior in videos. Most existing approaches explore the motion cue using optical flows. However, optical flow usually contains motion on both the interested human bodies and the undesired background. This "noisy" motion representation makes it very challenging for pose estimation and action recognition in real scenarios. To address this issue, this paper presents a novel deep motion representation, called PoseFlow, which reveals human motion in videos while suppressing background and motion blur, and being robust to occlusion. For learning PoseFlow with mild computational cost, we propose a functionally structured spatial-temporal deep network, PoseFlow Net (PFN), to jointly solve the skeleton localization and matching problems of PoseFlow. Comprehensive experiments show that PFN outperforms the state-of-the-art deep flow estimation models in generating PoseFlow. Moreover, PoseFlow demonstrates its potential on improving two challenging tasks in human video analysis: pose estimation and action recognition.
在视频中，人体的运动是理解和刻画人类行为的关键线索。大多数现有的方法使用光流来探索运动线索。然而，光流通常包含感兴趣的人体和不希望的背景上的运动。这种“嘈杂”的运动表示使得真实场景中的姿态估计和动作识别非常具有挑战性。为了解决这个问题，本文提出了一种新的深度运动表示，称为PoseFlow，它在抑制背景和运动模糊的同时显示视频中的人体运动，并且对遮挡具有鲁棒性。为了以较小的计算成本学习PoseFlow，我们提出了一种功能结构化的时空深度网络——PoseFlow Net (PFN)，共同解决PoseFlow的骨架定位和匹配问题。综合实验表明，PFN在生成PoseFlow方面优于最先进的深流估计模型。此外，PoseFlow展示了其在改进人类视频分析中两个具有挑战性的任务方面的潜力:姿势估计和动作识别。
{"title":"PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos","authors":"Dingwen Zhang, Guangyu Guo, Dong Huang, Junwei Han","doi":"10.1109/CVPR.2018.00707","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00707","url":null,"abstract":"Motion of the human body is the critical cue for understanding and characterizing human behavior in videos. Most existing approaches explore the motion cue using optical flows. However, optical flow usually contains motion on both the interested human bodies and the undesired background. This \"noisy\" motion representation makes it very challenging for pose estimation and action recognition in real scenarios. To address this issue, this paper presents a novel deep motion representation, called PoseFlow, which reveals human motion in videos while suppressing background and motion blur, and being robust to occlusion. For learning PoseFlow with mild computational cost, we propose a functionally structured spatial-temporal deep network, PoseFlow Net (PFN), to jointly solve the skeleton localization and matching problems of PoseFlow. Comprehensive experiments show that PFN outperforms the state-of-the-art deep flow estimation models in generating PoseFlow. Moreover, PoseFlow demonstrates its potential on improving two challenging tasks in human video analysis: pose estimation and action recognition.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"13 1","pages":"6762-6770"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84710834","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Benefiting from tens of millions of hierarchically stacked learnable parameters, Deep Neural Networks (DNNs) have demonstrated overwhelming accuracy on a variety of artificial intelligence tasks. However reversely, the large size of DNN models lays a heavy burden on storage, computation and power consumption, which prohibits their deployments on the embedded and mobile systems. In this paper, we propose Explicit Loss-error-aware Quantization (ELQ), a new method that can train DNN models with very low-bit parameter values such as ternary and binary ones to approximate 32-bit floating-point counterparts without noticeable loss of predication accuracy. Unlike existing methods that usually pose the problem as a straightforward approximation of the layer-wise weights or outputs of the original full-precision model (specifically, minimizing the error of the layer-wise weights or inner products of the weights and the inputs between the original and respective quantized models), our ELQ elaborately bridges the loss perturbation from the weight quantization and an incremental quantization strategy to address DNN quantization. Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective. As validated with two mainstream convolutional neural network families (i.e., fully convolutional and non-fully convolutional), our ELQ shows better results than state-of-the-art quantization methods on the large scale ImageNet classification dataset. Code will be made publicly available.
得益于数以千万计的分层堆叠的可学习参数，深度神经网络(dnn)在各种人工智能任务中表现出了压倒性的准确性。但反过来，DNN模型的大尺寸给存储、计算和功耗带来了沉重的负担，阻碍了其在嵌入式和移动系统上的部署。在本文中，我们提出了显式损失误差感知量化(Explicit loss -error-aware Quantization, ELQ)，这是一种新的方法，可以训练具有非常低比特参数值(如三元和二进制)的DNN模型来近似32位浮点值，而不会明显损失预测精度。与现有方法不同，现有方法通常将问题作为原始全精度模型的分层权重或输出的直接近似(具体而言，最小化分层权重的误差或权重的内积以及原始模型和各自量化模型之间的输入)，我们的ELQ精心地将来自权重量化和增量量化策略的损失扰动连接起来，以解决深度神经网络量化问题。通过对损失摄动和权值逼近误差的增量显式正则化，证明了这种优化方法在理论上是合理的，在实际应用中是有效的。通过两种主流卷积神经网络家族(即完全卷积和非完全卷积)的验证，我们的ELQ在大规模ImageNet分类数据集上显示出比最先进的量化方法更好的结果。代码将公开提供。
{"title":"Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks","authors":"Aojun Zhou, Anbang Yao, Kuan Wang, Yurong Chen","doi":"10.1109/CVPR.2018.00982","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00982","url":null,"abstract":"Benefiting from tens of millions of hierarchically stacked learnable parameters, Deep Neural Networks (DNNs) have demonstrated overwhelming accuracy on a variety of artificial intelligence tasks. However reversely, the large size of DNN models lays a heavy burden on storage, computation and power consumption, which prohibits their deployments on the embedded and mobile systems. In this paper, we propose Explicit Loss-error-aware Quantization (ELQ), a new method that can train DNN models with very low-bit parameter values such as ternary and binary ones to approximate 32-bit floating-point counterparts without noticeable loss of predication accuracy. Unlike existing methods that usually pose the problem as a straightforward approximation of the layer-wise weights or outputs of the original full-precision model (specifically, minimizing the error of the layer-wise weights or inner products of the weights and the inputs between the original and respective quantized models), our ELQ elaborately bridges the loss perturbation from the weight quantization and an incremental quantization strategy to address DNN quantization. Through explicitly regularizing the loss perturbation and the weight approximation error in an incremental way, we show that such a new optimization method is theoretically reasonable and practically effective. As validated with two mainstream convolutional neural network families (i.e., fully convolutional and non-fully convolutional), our ELQ shows better results than state-of-the-art quantization methods on the large scale ImageNet classification dataset. Code will be made publicly available.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"46 1","pages":"9426-9435"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88204691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we present a general-purpose solution to interactive texture transfer problems that better preserves both local structure and visual richness. It is challenging due to the diversity of tasks and the simplicity of required user guidance. The core idea of our common framework is to use multiple custom channels to dynamically guide the synthesis process. For interactivity, users can control the spatial distribution of stylized textures via semantic channels. The structure guidance, acquired by two stages of automatic extraction and propagation of structure information, provides a prior for initialization and preserves the salient structure by searching the nearest neighbor fields (NNF) with structure coherence. Meanwhile, texture coherence is also exploited to maintain similar style with the source image. In addition, we leverage an improved PatchMatch with extended NNF and matrix operations to obtain transformable source patches with richer geometric information at high speed. We demonstrate the effectiveness and superiority of our method on a variety of scenes through extensive comparisons with state-of-the-art algorithms.
{"title":"A Common Framework for Interactive Texture Transfer","authors":"Yifang Men, Z. Lian, Yingmin Tang, Jianguo Xiao","doi":"10.1109/CVPR.2018.00665","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00665","url":null,"abstract":"In this paper, we present a general-purpose solution to interactive texture transfer problems that better preserves both local structure and visual richness. It is challenging due to the diversity of tasks and the simplicity of required user guidance. The core idea of our common framework is to use multiple custom channels to dynamically guide the synthesis process. For interactivity, users can control the spatial distribution of stylized textures via semantic channels. The structure guidance, acquired by two stages of automatic extraction and propagation of structure information, provides a prior for initialization and preserves the salient structure by searching the nearest neighbor fields (NNF) with structure coherence. Meanwhile, texture coherence is also exploited to maintain similar style with the source image. In addition, we leverage an improved PatchMatch with extended NNF and matrix operations to obtain transformable source patches with richer geometric information at high speed. We demonstrate the effectiveness and superiority of our method on a variety of scenes through extensive comparisons with state-of-the-art algorithms.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"53 1","pages":"6353-6362"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90954518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multi-layer light field displays are a type of computational three-dimensional (3D) display which has recently gained increasing interest for its holographic-like effect and natural compatibility with 2D displays. However, the major shortcoming, depth limitation, still cannot be overcome in the traditional light field modeling and reconstruction based on multi-layer liquid crystal displays (LCDs). Considering this disadvantage, our paper incorporates a salience guided depth optimization over a limited display range to calibrate the displayed depth and present the maximum area of salience region for multi-layer light field display. Different from previously reported cascaded light field displays that use the fixed initialization plane as the depth center of display content, our method automatically calibrates the depth initialization based on the salience results derived from the proposed contrast enhanced salience detection method. Experiments demonstrate that the proposed method provides a promising advantage in visual perception for the compressive light field displays from both software simulation and prototype demonstration.
{"title":"Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display","authors":"Shizheng Wang, Wenjuan Liao, P. Surman, Zhigang Tu, Yuanjin Zheng, Junsong Yuan","doi":"10.1109/CVPR.2018.00217","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00217","url":null,"abstract":"Multi-layer light field displays are a type of computational three-dimensional (3D) display which has recently gained increasing interest for its holographic-like effect and natural compatibility with 2D displays. However, the major shortcoming, depth limitation, still cannot be overcome in the traditional light field modeling and reconstruction based on multi-layer liquid crystal displays (LCDs). Considering this disadvantage, our paper incorporates a salience guided depth optimization over a limited display range to calibrate the displayed depth and present the maximum area of salience region for multi-layer light field display. Different from previously reported cascaded light field displays that use the fixed initialization plane as the depth center of display content, our method automatically calibrates the depth initialization based on the salience results derived from the proposed contrast enhanced salience detection method. Experiments demonstrate that the proposed method provides a promising advantage in visual perception for the compressive light field displays from both software simulation and prototype demonstration.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"62 1","pages":"2031-2040"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77902099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：