检索结果-南通市图书馆

mask-aware photorealistic facial attribute manipulation

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第3期7卷 363-374页

作者： Ruoqi Sun Chen Huang Hengliang Zhu lizhuang ma Shanghai Jiao Tong University Shanghai 200240China Robotics Institute Carnegie Mellon UniversityPittsburghPA15213USA

The technique of facial attribute manipulation has found increasing application,but it remains challenging to restrict editing of attributes so that a face’s unique details are *** this paper,we introduce our method,which we call a mask-adversarial autoencoder(M-AAE).It combines a variational autoencoder(VAE)and a generative adversarial network(GAN)for photorealistic image *** use partial dilated layers to modify a few pixels in the feature maps of an encoder,changing the attribute strength continuously without hindering global *** training objectives for the VAE and GAN are reinforced by supervision of face recognition loss and cycle consistency loss,to faithfully preserve facial ***,we generate facial masks to enforce background consistency,which allows our training to focus on the foreground face rather than the *** results demonstrate that our method can generate high-quality images with varying attributes,and outperforms existing methods in detail preservation.

关键词： face attribute manipulation generative adversarial network(GAN) variational autoencoder(VAE) partial dilated layers photorealism

Digital image inpainting by example-based image synthesis method

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2006年第3期12卷 276-282页

作者：聂栋栋 ma lizhuang Xiao Shuangjiu Computer Science ＆ Engineering Department Shanghai Jiaotong University Shanghai 200240 P.R. China School of Software Shanghai Jiaotong University Shanghai 200240 P. R. China

A simple and effective image inpainting method is proposed in this paper, which is proved to be suitable for different kinds of target regions with shapes from little scraps to large unseemly objects in a wide range of images. It is an important improvement upon the traditional image inpainting techniques. By introducing a new bijeetive-mapping term into the matching cost function, the artificial repetition problem in the final inpainting image is practically solved. In addition, by adopting an inpainting error map, not only the target pixels are refined gradually during the inpainting process but also the overlapped target patches are combined more seamlessly than previous method. Finally, the inpainting time is dramatically decreased by using a new acceleration method in the matching process.

关键词： inpainting image synthesis texture synthesis prority matching cost function example patch isophote diffusion

Shape recovery using high dynamic range images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2008年第4期14卷 384-389页

作者：郑作勇 ma lizhuang Li Zhong Department of Computer Science Shanghai.Jiao Tong University Shanghai 2002A0 P.R. China Department of Applied mathematics Zhejiang Sci-Tech University Hangzhou 310018 P.R. China

An effective method for object shape recovery using HDRIs （high dynamic range images） is proposed. The radiance values of each point on the reference sphere and target object are firstly calculated, thus the set of candidate normals of each target point are found by comparing its radiance to that of each reference sphere point. In single-image shape recovery, a smoothness operation is applied to the target normals to obtain a stable and reasonable result; while in photometric stereo, radiance vectors of reference and target objects formed due to illuminations under different fight source directions are directly compared to get the most suitable target normals. Finally, the height values can be recovered from the resulting normal field. Because diffuse and specular reflection are handled in an unified framework with radiance, our approach eliminates the limitation presented in most recovery strategies, i.e., only Lambertian model can be used. The experiment results from the real and synthesized images show the performance of our approach.

关键词： shape recovery high dynamic range image bidirectional reflectance distribution function (BRDF) reflectance map photometric stereo

Reverse Loop subdivision with sharp features

在线全文

学校读者我要写书评

暂无评论

High Technology Letters 2006年第2期12卷 113-118页

作者：赵明喜 ma lizhuang mao Zhihong Wu Xiaomao Department of Computer Science and Engineering Shanghai Jiaotong University Shanghai 200030 P. R. China

In this paper we introduce a new reverse Loop subdivision method. In contrast to current wavelets based Loop subdivision scheme, our method applies the same rules to both regular and extraordinary vertices and reconstructs the sharp features easily. Furthermore, our method runs faster because it does not need analysis and synthesis procedural. Our main goal is the design of a reverse subdivision method that can reconstruct the coarser mesh from a finer subdivision surface with sharp features for multiresolution representation, The proposed method only needs a little memory storage and brings little error, and it is easy to implement.

关键词： reverse subdivision Loop subdivision sharp features multiresolution

A motion retargeting algorithm based on model simplification

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2005年第3期11卷 225-228页

作者： Chen Zhihua（陈志华） ma lizhuang Wu Xiaomao Gao Yan Department of Computer Science ＆ Engineering Shanghai Jiaotong University Shanghai 200030 P.R. China

A new motion retargeting algorithm is presented, which adapts me motion capture data to a new character. To make the resulting motion realistic, the physically-based optimization method is adopted. However, the optimization process is difficult to converge to the optimal value because of high complexity of the physical human model. In order to address this problem, an appropriate simplified model automatically determined by a motion analysis technique is utilized, and then motion retargeting with this simplified model as an intermediate agent is implemented. The entire motion retargeting algorithm involves three steps of nonlinearly constrained optimization： forward retargeting, motion scaling and inverse retargeting. Experimental results show the validity of this algorithm.

关键词： computer graphics computer animation motion capture motion retargeting

Edge-preserving image decomposition via joint weighted least squares

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2015年第1期1卷 37-47页

作者： Pan Shao Shouhong Ding lizhuang ma Yunsheng Wu Yongjian Wu Department of Computer Science and Engineering Shanghai Jiao Tong University Tencent Inc.

Recent years have witnessed the emergence of image decomposition techniques which effectively separate an image into a piecewise smooth base layer and several residual detail layers. However, the intricacy of detail patterns in some cases may result in side-effects including remnant textures, wronglysmoothed edges, and distorted appearance. We introduce a new way to construct an edge-preserving image decomposition with properties of detail smoothing, edge retention, and shape fitting. Our method has three main steps: suppressing highcontrast details via a windowed variation similarity measure, detecting salient edges to produce an edgeguided image, and fitting the original shape using a weighted least squares framework. Experimental results indicate that the proposed approach can appropriately smooth non-edge regions even when textures and structures are similar in scale. The effectiveness of our approach is demonstrated in the contexts of detail manipulation, HDR tone mapping,and image abstraction.

关键词： detail suppression edge extraction edge-preserving decomposition shape recovery

Confusing Object Detection:A Survey

在线全文

学校读者我要写书评

暂无评论

Computers, materials & Continua 2024年第9期80卷 3421-3461页

作者： Kunkun Tong Guchu Zou Xin Tan Jingyu Gong Zhenyi Qi Zhizhong Zhang Yuan Xie lizhuang ma School of Computer Science and Technology East China Normal UniversityShanghai200062China Shanghai Institute of Ceramics Chinese Academy of SciencesShanghai200050China

Confusing object detection(COD),such as glass,mirrors,and camouflaged objects,represents a burgeoning visual detection task centered on pinpointing and distinguishing concealed targets within intricate backgrounds,leveraging deep learning *** garnering increasing attention in computer vision,the focus of most existing works leans toward formulating task-specific solutions rather than delving into in-depth analyses of methodological *** of now,there is a notable absence of a comprehensive systematic review that focuses on recently proposed deep learning-based models for these specific *** fill this gap,our study presents a pioneering review that covers both themodels and the publicly available benchmark datasets,while also identifying potential directions for future research in this *** current dataset primarily focuses on single confusing object detection at the image level,with some studies extending to video-level *** conduct an in-depth analysis of deep learning architectures,revealing that the current state-of-the-art(SOTA)COD methods demonstrate promising performance in single object *** also compile and provide detailed descriptions ofwidely used datasets relevant to these detection *** endeavor extends to discussing the limitations observed in current methodologies,alongside proposed solutions aimed at enhancing detection ***,we deliberate on relevant applications and outline future research trajectories,aiming to catalyze advancements in the field of glass,mirror,and camouflaged object detection.

关键词： Confusing object detection mirror detection glass detection camouflaged object detection deep learning

RADepthNet:Reflectance-aware monocular depth estimation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2022年第5期4卷 418-431页

作者： Chuxuan LI Ran YI Saba Ghazanfar ALI lizhuang ma Enhua WU Jihong WANG Lijuan maO Bin SHENG Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Department of State Key Laboratory of Computer Science University of MacaoMacao 999078China Shanghai University of Sports Shanghai 200438China

Background Monocular depth estimation aims to predict a dense depth map from a single RGB image,and has important applications in 3D reconstruction,automatic driving,and augmented ***,existing methods directly feed the original RGB image into the model to extract depth features without avoiding the interference of depth-irrelevant information on depth-estimation accuracy,which leads to inferior *** To remove the influence of depth-irrelevant information and improve the depth-prediction accuracy,we propose RADepthNet,a novel reflectance-guided network that fuses boundary ***,our method predicts depth maps using the following three steps:(1)Intrinsic Image *** propose a reflectance extraction module consisting of an encoder-decoder structure to extract the depth-related *** an ablation study,we demonstrate that the module can reduce the influence of illumination on depth estimation.(2)Boundary Detection.A boundary extraction module,consisting of an encoder,refinement block,and upsample block,was proposed to better predict the depth at object boundaries utilizing gradient constraints.(3)Depth Prediction *** use an encoder different from(2)to obtain depth features from the reflectance map and fuse boundary features to predict *** addition,we proposed FIFADataset,a depth-estimation dataset applied in soccer *** Extensive experiments on a public dataset and our proposed FIFADataset show that our method achieves state-of-the-art performance.

关键词： Monocular depth estimation Deep learning Intrinsic image decomposition

The Effects of Shape Parameters for Surface Joining with High Order Geometric Continuity

在线全文

学校读者我要写书评

暂无评论

Computer Aided Drafting,Design and manufacturing 1998年第1期8卷 20-28页

作者： Lu Xiaolin ma lizhuang He Zhijun 2

The necessary and sufficient conditions and an algorithm to reach continuity between adjacent Bézier patches are presented. The effects of shape parameters for surface connection of G4 geometric continuity are investigated in detail. The algorithm can be generalized directly to the case of surface joining with higher order geometric continuity. It has important applications in surface modeling and surface joining.

关键词： Bézier surface surface modeling geometric continuity