Jingchun Cheng, Yi-Hsuan Tsai, Wei-Chih Hung, Shengjin Wang, Ming-Hsuan Yang
Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.
{"title":"Fast and Accurate Online Video Object Segmentation via Tracking Parts","authors":"Jingchun Cheng, Yi-Hsuan Tsai, Wei-Chih Hung, Shengjin Wang, Ming-Hsuan Yang","doi":"10.1109/CVPR.2018.00774","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00774","url":null,"abstract":"Online video object segmentation is a challenging task as it entails to process the image sequence timely and accurately. To segment a target object through the video, numerous CNN-based methods have been developed by heavily finetuning on the object mask in the first frame, which is time-consuming for online applications. In this paper, we propose a fast and accurate video object segmentation algorithm that can immediately start the segmentation process once receiving the images. We first utilize a part-based tracking method to deal with challenging factors such as large deformation, occlusion, and cluttered background. Based on the tracked bounding boxes of parts, we construct a region-of-interest segmentation network to generate part masks. Finally, a similarity-based scoring function is adopted to refine these object parts by comparing them to the visual information in the first frame. Our method performs favorably against state-of-the-art algorithms in accuracy on the DAVIS benchmark dataset, while achieving much faster runtime performance.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"25 1","pages":"7415-7424"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75071450","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}
Vasili Ramanishka, Yi-Ting Chen, Teruhisa Misu, Kate Saenko
Driving Scene understanding is a key ingredient for intelligent transportation systems. To achieve systems that can operate in a complex physical and social environment, they need to understand and learn how humans drive and interact with traffic scenes. We present the Honda Research Institute Driving Dataset (HDD), a challenging dataset to enable research on learning driver behavior in real-life environments. The dataset includes 104 hours of real human driving in the San Francisco Bay Area collected using an instrumented vehicle equipped with different sensors. We provide a detailed analysis of HDD with a comparison to other driving datasets. A novel annotation methodology is introduced to enable research on driver behavior understanding from untrimmed data sequences. As the first step, baseline algorithms for driver behavior detection are trained and tested to demonstrate the feasibility of the proposed task.
{"title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","authors":"Vasili Ramanishka, Yi-Ting Chen, Teruhisa Misu, Kate Saenko","doi":"10.1109/CVPR.2018.00803","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00803","url":null,"abstract":"Driving Scene understanding is a key ingredient for intelligent transportation systems. To achieve systems that can operate in a complex physical and social environment, they need to understand and learn how humans drive and interact with traffic scenes. We present the Honda Research Institute Driving Dataset (HDD), a challenging dataset to enable research on learning driver behavior in real-life environments. The dataset includes 104 hours of real human driving in the San Francisco Bay Area collected using an instrumented vehicle equipped with different sensors. We provide a detailed analysis of HDD with a comparison to other driving datasets. A novel annotation methodology is introduced to enable research on driver behavior understanding from untrimmed data sequences. As the first step, baseline algorithms for driver behavior detection are trained and tested to demonstrate the feasibility of the proposed task.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"26 1","pages":"7699-7707"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75441246","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}
Mingmin Zhao, Tianhong Li, Mohammad Abu Alsheikh, Yonglong Tian, Hang Zhao, A. Torralba, D. Katabi
This paper demonstrates accurate human pose estimation through walls and occlusions. We leverage the fact that wireless signals in the WiFi frequencies traverse walls and reflect off the human body. We introduce a deep neural network approach that parses such radio signals to estimate 2D poses. Since humans cannot annotate radio signals, we use state-of-the-art vision model to provide cross-modal supervision. Specifically, during training the system uses synchronized wireless and visual inputs, extracts pose information from the visual stream, and uses it to guide the training process. Once trained, the network uses only the wireless signal for pose estimation. We show that, when tested on visible scenes, the radio-based system is almost as accurate as the vision-based system used to train it. Yet, unlike vision-based pose estimation, the radio-based system can estimate 2D poses through walls despite never trained on such scenarios. Demo videos are available at our website.
{"title":"Through-Wall Human Pose Estimation Using Radio Signals","authors":"Mingmin Zhao, Tianhong Li, Mohammad Abu Alsheikh, Yonglong Tian, Hang Zhao, A. Torralba, D. Katabi","doi":"10.1109/CVPR.2018.00768","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00768","url":null,"abstract":"This paper demonstrates accurate human pose estimation through walls and occlusions. We leverage the fact that wireless signals in the WiFi frequencies traverse walls and reflect off the human body. We introduce a deep neural network approach that parses such radio signals to estimate 2D poses. Since humans cannot annotate radio signals, we use state-of-the-art vision model to provide cross-modal supervision. Specifically, during training the system uses synchronized wireless and visual inputs, extracts pose information from the visual stream, and uses it to guide the training process. Once trained, the network uses only the wireless signal for pose estimation. We show that, when tested on visible scenes, the radio-based system is almost as accurate as the vision-based system used to train it. Yet, unlike vision-based pose estimation, the radio-based system can estimate 2D poses through walls despite never trained on such scenarios. Demo videos are available at our website.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"95 1","pages":"7356-7365"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75452796","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}
We introduce the light localization problem. A scene is illuminated by a set of unobserved isotropic point lights. Given the geometry, materials, and illuminated, appearance of the scene, the light localization problem is to completely recover the number, positions, and intensities of the lights. We first present a scene transform that identifies likely light positions. Based on this transform, we develop an iterative algorithm to locate remaining lights and determine all light intensities. We demonstrate the success of this method in a large set of 2D synthetic scenes, and show that it extends to 3D, in both synthetic scenes and real-world scenes.
{"title":"Discovering Point Lights with Intensity Distance Fields","authors":"Edward Zhang, Michael F. Cohen, B. Curless","doi":"10.1109/CVPR.2018.00694","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00694","url":null,"abstract":"We introduce the light localization problem. A scene is illuminated by a set of unobserved isotropic point lights. Given the geometry, materials, and illuminated, appearance of the scene, the light localization problem is to completely recover the number, positions, and intensities of the lights. We first present a scene transform that identifies likely light positions. Based on this transform, we develop an iterative algorithm to locate remaining lights and determine all light intensities. We demonstrate the success of this method in a large set of 2D synthetic scenes, and show that it extends to 3D, in both synthetic scenes and real-world scenes.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"8 1","pages":"6635-6643"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75455062","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}
Large-scale 3D point clouds (LS3DPCs) captured by terrestrial LiDAR scanners often exhibit reflection artifacts by glasses, which degrade the performance of related computer vision techniques. In this paper, we propose an efficient reflection removal algorithm for LS3DPCs. We first partition the unit sphere into local surface patches which are then classified into the ordinary patches and the glass patches according to the number of echo pulses from emitted laser pulses. Then we estimate the glass region of dominant reflection artifacts by measuring the reliability. We also detect and remove the virtual points using the conditions of the reflection symmetry and the geometric similarity. We test the performance of the proposed algorithm on LS3DPCs capturing real-world outdoor scenes, and show that the proposed algorithm estimates valid glass regions faithfully and removes the virtual points caused by reflection artifacts successfully.
{"title":"Reflection Removal for Large-Scale 3D Point Clouds","authors":"J. Yun, Jae-Young Sim","doi":"10.1109/CVPR.2018.00483","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00483","url":null,"abstract":"Large-scale 3D point clouds (LS3DPCs) captured by terrestrial LiDAR scanners often exhibit reflection artifacts by glasses, which degrade the performance of related computer vision techniques. In this paper, we propose an efficient reflection removal algorithm for LS3DPCs. We first partition the unit sphere into local surface patches which are then classified into the ordinary patches and the glass patches according to the number of echo pulses from emitted laser pulses. Then we estimate the glass region of dominant reflection artifacts by measuring the reliability. We also detect and remove the virtual points using the conditions of the reflection symmetry and the geometric similarity. We test the performance of the proposed algorithm on LS3DPCs capturing real-world outdoor scenes, and show that the proposed algorithm estimates valid glass regions faithfully and removes the virtual points caused by reflection artifacts successfully.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"29 1","pages":"4597-4605"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77973057","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}
Daniel Teo, Boxin Shi, Yinqiang Zheng, Sai-Kit Yeung
We present a self-calibrating polarising radiometric calibration method. From a set of images taken from a single viewpoint under different unknown polarising angles, we recover the inverse camera response function and the polarising angles relative to the first angle. The problem is solved in an integrated manner, recovering both of the unknowns simultaneously. The method exploits the fact that the intensity of polarised light should vary sinusoidally as the polarising filter is rotated, provided that the response is linear. It offers the first solution to demonstrate the possibility of radiometric calibration through polarisation. We evaluate the accuracy of our proposed method using synthetic data and real world objects captured using different cameras. The self-calibrated results were found to be comparable with those from multiple exposure sequence.
{"title":"Self-Calibrating Polarising Radiometric Calibration","authors":"Daniel Teo, Boxin Shi, Yinqiang Zheng, Sai-Kit Yeung","doi":"10.1109/CVPR.2018.00299","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00299","url":null,"abstract":"We present a self-calibrating polarising radiometric calibration method. From a set of images taken from a single viewpoint under different unknown polarising angles, we recover the inverse camera response function and the polarising angles relative to the first angle. The problem is solved in an integrated manner, recovering both of the unknowns simultaneously. The method exploits the fact that the intensity of polarised light should vary sinusoidally as the polarising filter is rotated, provided that the response is linear. It offers the first solution to demonstrate the possibility of radiometric calibration through polarisation. We evaluate the accuracy of our proposed method using synthetic data and real world objects captured using different cameras. The self-calibrated results were found to be comparable with those from multiple exposure sequence.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"256 1","pages":"2831-2839"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73112827","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}
This paper re-visits classical problems in document enhancement. Rather than proposing a new algorithm for a specific problem, we introduce a novel general approach. The key idea is to modify any state-of-the-art algorithm, by providing it with new information (input), improving its own results. Interestingly, this information is based on a solution to a seemingly unrelated problem of visibility detection in R3. We show that a simple representation of an image as a 3D point cloud, gives visibility detection on this cloud a new interpretation. What does it mean for a point to be visible? Although this question has been widely studied within computer vision, it has always been assumed that the point set is a sampling of a real scene. We show that the answer to this question in our context reveals unique and useful information about the image. We demonstrate the benefit of this idea for document binarization and for unshadowing.
{"title":"Document Enhancement Using Visibility Detection","authors":"Netanel Kligler, S. Katz, A. Tal","doi":"10.1109/CVPR.2018.00252","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00252","url":null,"abstract":"This paper re-visits classical problems in document enhancement. Rather than proposing a new algorithm for a specific problem, we introduce a novel general approach. The key idea is to modify any state-of-the-art algorithm, by providing it with new information (input), improving its own results. Interestingly, this information is based on a solution to a seemingly unrelated problem of visibility detection in R3. We show that a simple representation of an image as a 3D point cloud, gives visibility detection on this cloud a new interpretation. What does it mean for a point to be visible? Although this question has been widely studied within computer vision, it has always been assumed that the point set is a sampling of a real scene. We show that the answer to this question in our context reveals unique and useful information about the image. We demonstrate the benefit of this idea for document binarization and for unshadowing.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"2019 1","pages":"2374-2382"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72667501","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 simple yet effective method to learn globally optimized detector for object detection, which is a simple modification to the standard cross-entropy gradient inspired by the REINFORCE algorithm. In our approach, the cross-entropy gradient is adaptively adjusted according to overall mean Average Precision (mAP) of the current state for each detection candidate, which leads to more effective gradient and global optimization of detection results, and brings no computational overhead. Benefiting from more precise gradients produced by the global optimization method, our framework significantly improves state-of-the-art object detectors. Furthermore, since our method is based on scores and bounding boxes without modification on the architecture of object detector, it can be easily applied to off-the-shelf modern object detection frameworks.
{"title":"Learning Globally Optimized Object Detector via Policy Gradient","authors":"Yongming Rao, Dahua Lin, Jiwen Lu, Jie Zhou","doi":"10.1109/CVPR.2018.00648","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00648","url":null,"abstract":"In this paper, we propose a simple yet effective method to learn globally optimized detector for object detection, which is a simple modification to the standard cross-entropy gradient inspired by the REINFORCE algorithm. In our approach, the cross-entropy gradient is adaptively adjusted according to overall mean Average Precision (mAP) of the current state for each detection candidate, which leads to more effective gradient and global optimization of detection results, and brings no computational overhead. Benefiting from more precise gradients produced by the global optimization method, our framework significantly improves state-of-the-art object detectors. Furthermore, since our method is based on scores and bounding boxes without modification on the architecture of object detector, it can be easily applied to off-the-shelf modern object detection frameworks.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"2 1","pages":"6190-6198"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73776515","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}
This paper introduces an automatic method for editing a portrait photo so that the subject appears to be wearing makeup in the style of another person in a reference photo. Our unsupervised learning approach relies on a new framework of cycle-consistent generative adversarial networks. Different from the image domain transfer problem, our style transfer problem involves two asymmetric functions: a forward function encodes example-based style transfer, whereas a backward function removes the style. We construct two coupled networks to implement these functions - one that transfers makeup style and a second that can remove makeup - such that the output of their successive application to an input photo will match the input. The learned style network can then quickly apply an arbitrary makeup style to an arbitrary photo. We demonstrate the effectiveness on a broad range of portraits and styles.
{"title":"PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup","authors":"Huiwen Chang, Jingwan Lu, F. Yu, Adam Finkelstein","doi":"10.1109/CVPR.2018.00012","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00012","url":null,"abstract":"This paper introduces an automatic method for editing a portrait photo so that the subject appears to be wearing makeup in the style of another person in a reference photo. Our unsupervised learning approach relies on a new framework of cycle-consistent generative adversarial networks. Different from the image domain transfer problem, our style transfer problem involves two asymmetric functions: a forward function encodes example-based style transfer, whereas a backward function removes the style. We construct two coupled networks to implement these functions - one that transfers makeup style and a second that can remove makeup - such that the output of their successive application to an input photo will match the input. The learned style network can then quickly apply an arbitrary makeup style to an arbitrary photo. We demonstrate the effectiveness on a broad range of portraits and styles.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"65 1","pages":"40-48"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84349314","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 work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely-connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian Conditional Random Fields (GCRFs). Our method, called VideoGCRF is (a) efficient, (b) has a unique global minimum, and (c) can be trained end-to-end alongside contemporary deep networks for video understanding. We experiment with multiple connectivity patterns in the temporal domain, and present empirical improvements over strong baselines on the tasks of both semantic and instance segmentation of videos. Our implementation is based on the Caffe2 framework and will be available at https://github.com/siddharthachandra/gcrf-v3.0.
{"title":"Deep Spatio-Temporal Random Fields for Efficient Video Segmentation","authors":"Siddhartha Chandra, C. Couprie, Iasonas Kokkinos","doi":"10.1109/CVPR.2018.00929","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00929","url":null,"abstract":"In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely-connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian Conditional Random Fields (GCRFs). Our method, called VideoGCRF is (a) efficient, (b) has a unique global minimum, and (c) can be trained end-to-end alongside contemporary deep networks for video understanding. We experiment with multiple connectivity patterns in the temporal domain, and present empirical improvements over strong baselines on the tasks of both semantic and instance segmentation of videos. Our implementation is based on the Caffe2 framework and will be available at https://github.com/siddharthachandra/gcrf-v3.0.","PeriodicalId":6564,"journal":{"name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","volume":"51 1","pages":"8915-8924"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84773381","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：