2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第4页

SUN RGB-D: A RGB-D scene understanding benchmark suite SUN RGB-D:一个RGB-D场景理解基准套件

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298655

Shuran Song, Samuel P. Lichtenberg, Jianxiong Xiao

引用次数: 1433

Inferring 3D layout of building facades from a single image 从单个图像推断建筑立面的3D布局

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298910

Jiyan Pan, M. Hebert, T. Kanade

引用次数: 13

Global supervised descent method 全局监督下降法

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298882

Xuehan Xiong, F. D. L. Torre

{"title":"Global supervised descent method","authors":"Xuehan Xiong, F. D. L. Torre","doi":"10.1109/CVPR.2015.7298882","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298882","url":null,"abstract":"Mathematical optimization plays a fundamental role in solving many problems in computer vision (e.g., camera calibration, image alignment, structure from motion). It is generally accepted that second order descent methods are the most robust, fast, and reliable approaches for nonlinear optimization of a general smooth function. However, in the context of computer vision, second order descent methods have two main drawbacks: 1) the function might not be analytically differentiable and numerical approximations are impractical, and 2) the Hessian may be large and not positive definite. Recently, Supervised Descent Method (SDM), a method that learns the “weighted averaged gradients” in a supervised manner has been proposed to solve these issues. However, SDM is a local algorithm and it is likely to average conflicting gradient directions. This paper proposes Global SDM (GSDM), an extension of SDM that divides the search space into regions of similar gradient directions. GSDM provides a better and more efficient strategy to minimize non-linear least squares functions in computer vision problems. We illustrate the effectiveness of GSDM in two problems: non-rigid image alignment and extrinsic camera calibration.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125421635","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}

引用次数: 209

A MRF shape prior for facade parsing with occlusions 具有遮挡的facade解析的MRF形状

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298899

M. Koziński, Raghudeep Gadde, Sergey Zagoruyko, G. Obozinski, R. Marlet

引用次数: 46

What do 15,000 object categories tell us about classifying and localizing actions? 15,000个对象类别告诉我们关于分类和定位动作的什么信息?

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298599

Mihir Jain, J. V. Gemert, Cees G. M. Snoek

引用次数: 185

Hierarchical sparse coding with geometric prior for visual geo-location 基于几何先验的视觉地理定位分层稀疏编码

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298857

Raghuraman Gopalan

引用次数: 10

Object-based RGBD image co-segmentation with mutex constraint 基于对象的RGBD图像互锁共分割

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7299072

H. Fu, Dong Xu, Stephen Lin, Jiang Liu

引用次数: 96

Video summarization by learning submodular mixtures of objectives 视频摘要通过学习子模块混合目标

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298928

Michael Gygli, H. Grabner, L. Gool

引用次数: 389

Towards unified depth and semantic prediction from a single image 对单幅图像进行统一深度和语义预测

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298897

Peng Wang, Xiaohui Shen, Zhe L. Lin, Scott D. Cohen, Brian L. Price, A. Yuille

{"title":"Towards unified depth and semantic prediction from a single image","authors":"Peng Wang, Xiaohui Shen, Zhe L. Lin, Scott D. Cohen, Brian L. Price, A. Yuille","doi":"10.1109/CVPR.2015.7298897","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298897","url":null,"abstract":"Depth estimation and semantic segmentation are two fundamental problems in image understanding. While the two tasks are strongly correlated and mutually beneficial, they are usually solved separately or sequentially. Motivated by the complementary properties of the two tasks, we propose a unified framework for joint depth and semantic prediction. Given an image, we first use a trained Convolutional Neural Network (CNN) to jointly predict a global layout composed of pixel-wise depth values and semantic labels. By allowing for interactions between the depth and semantic information, the joint network provides more accurate depth prediction than a state-of-the-art CNN trained solely for depth prediction [6]. To further obtain fine-level details, the image is decomposed into local segments for region-level depth and semantic prediction under the guidance of global layout. Utilizing the pixel-wise global prediction and region-wise local prediction, we formulate the inference problem in a two-layer Hierarchical Conditional Random Field (HCRF) to produce the final depth and semantic map. As demonstrated in the experiments, our approach effectively leverages the advantages of both tasks and provides the state-of-the-art results.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133247118","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}

引用次数: 409

Joint SFM and detection cues for monocular 3D localization in road scenes 联合SFM和检测线索用于道路场景的单目3D定位

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2015-06-07 DOI: 10.1109/CVPR.2015.7298997

Shiyu Song, Manmohan Chandraker

{"title":"Joint SFM and detection cues for monocular 3D localization in road scenes","authors":"Shiyu Song, Manmohan Chandraker","doi":"10.1109/CVPR.2015.7298997","DOIUrl":"https://doi.org/10.1109/CVPR.2015.7298997","url":null,"abstract":"We present a system for fast and highly accurate 3D localization of objects like cars in autonomous driving applications, using a single camera. Our localization framework jointly uses information from complementary modalities such as structure from motion (SFM) and object detection to achieve high localization accuracy in both near and far fields. This is in contrast to prior works that rely purely on detector outputs, or motion segmentation based on sparse feature tracks. Rather than completely commit to tracklets generated by a 2D tracker, we make novel use of raw detection scores to allow our 3D bounding boxes to adapt to better quality 3D cues. To extract SFM cues, we demonstrate the advantages of dense tracking over sparse mechanisms in autonomous driving scenarios. In contrast to complex scene understanding, our formulation for 3D localization is efficient and can be regarded as an extension of sparse bundle adjustment to incorporate object detection cues. Experiments on the KITTI dataset show the efficacy of our cues, as well as the accuracy and robustness of our 3D object localization relative to ground truth and prior works.","PeriodicalId":444472,"journal":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115855372","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}

引用次数: 86