Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng
This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level tasks on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN, we witness a large improvement of the object detection performance on hazy images.
{"title":"AOD-Net: All-in-One Dehazing Network","authors":"Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, Dan Feng","doi":"10.1109/ICCV.2017.511","DOIUrl":"https://doi.org/10.1109/ICCV.2017.511","url":null,"abstract":"This paper proposes an image dehazing model built with a convolutional neural network (CNN), called All-in-One Dehazing Network (AOD-Net). It is designed based on a re-formulated atmospheric scattering model. Instead of estimating the transmission matrix and the atmospheric light separately as most previous models did, AOD-Net directly generates the clean image through a light-weight CNN. Such a novel end-to-end design makes it easy to embed AOD-Net into other deep models, e.g., Faster R-CNN, for improving high-level tasks on hazy images. Experimental results on both synthesized and natural hazy image datasets demonstrate our superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality. Furthermore, when concatenating AOD-Net with Faster R-CNN, we witness a large improvement of the object detection performance on hazy images.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"17 1","pages":"4780-4788"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74781172","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}
Zhoutong Zhang, Jiajun Wu, Qiujia Li, Zhengjia Huang, James Traer, Josh H. McDermott, J. Tenenbaum, W. Freeman
Humans infer rich knowledge of objects from both auditory and visual cues. Building a machine of such competency, however, is very challenging, due to the great difficulty in capturing large-scale, clean data of objects with both their appearance and the sound they make. In this paper, we present a novel, open-source pipeline that generates audiovisual data, purely from 3D object shapes and their physical properties. Through comparison with audio recordings and human behavioral studies, we validate the accuracy of the sounds it generates. Using this generative model, we are able to construct a synthetic audio-visual dataset, namely Sound-20K, for object perception tasks. We demonstrate that auditory and visual information play complementary roles in object perception, and further, that the representation learned on synthetic audio-visual data can transfer to real-world scenarios.
{"title":"Generative Modeling of Audible Shapes for Object Perception","authors":"Zhoutong Zhang, Jiajun Wu, Qiujia Li, Zhengjia Huang, James Traer, Josh H. McDermott, J. Tenenbaum, W. Freeman","doi":"10.1109/ICCV.2017.141","DOIUrl":"https://doi.org/10.1109/ICCV.2017.141","url":null,"abstract":"Humans infer rich knowledge of objects from both auditory and visual cues. Building a machine of such competency, however, is very challenging, due to the great difficulty in capturing large-scale, clean data of objects with both their appearance and the sound they make. In this paper, we present a novel, open-source pipeline that generates audiovisual data, purely from 3D object shapes and their physical properties. Through comparison with audio recordings and human behavioral studies, we validate the accuracy of the sounds it generates. Using this generative model, we are able to construct a synthetic audio-visual dataset, namely Sound-20K, for object perception tasks. We demonstrate that auditory and visual information play complementary roles in object perception, and further, that the representation learned on synthetic audio-visual data can transfer to real-world scenarios.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"38 1","pages":"1260-1269"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72877952","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}
Tao Yu, Kaiwen Guo, F. Xu, Yuan Dong, Zhaoqi Su, Jianhui Zhao, Jianguo Li, Qionghai Dai, Yebin Liu
We propose BodyFusion, a novel real-time geometry fusion method that can track and reconstruct non-rigid surface motion of a human performance using a single consumer-grade depth camera. To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method. The key feature of our method is that it jointly solves for both the skeleton and graph-node deformations based on information of the attachments between the skeleton and the graph nodes. The attachments are also updated frame by frame based on the fused surface geometry and the computed deformations. Overall, our method enables increasingly denoised, detailed, and complete surface reconstruction as well as the updating of the skeleton and attachments as the temporal depth frames are fused. Experimental results show that our method exhibits substantially improved nonrigid motion fusion performance and tracking robustness compared with previous state-of-the-art fusion methods. We also contribute a dataset for the quantitative evaluation of fusion-based dynamic scene reconstruction algorithms using a single depth camera.
{"title":"BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera","authors":"Tao Yu, Kaiwen Guo, F. Xu, Yuan Dong, Zhaoqi Su, Jianhui Zhao, Jianguo Li, Qionghai Dai, Yebin Liu","doi":"10.1109/ICCV.2017.104","DOIUrl":"https://doi.org/10.1109/ICCV.2017.104","url":null,"abstract":"We propose BodyFusion, a novel real-time geometry fusion method that can track and reconstruct non-rigid surface motion of a human performance using a single consumer-grade depth camera. To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method. The key feature of our method is that it jointly solves for both the skeleton and graph-node deformations based on information of the attachments between the skeleton and the graph nodes. The attachments are also updated frame by frame based on the fused surface geometry and the computed deformations. Overall, our method enables increasingly denoised, detailed, and complete surface reconstruction as well as the updating of the skeleton and attachments as the temporal depth frames are fused. Experimental results show that our method exhibits substantially improved nonrigid motion fusion performance and tracking robustness compared with previous state-of-the-art fusion methods. We also contribute a dataset for the quantitative evaluation of fusion-based dynamic scene reconstruction algorithms using a single depth camera.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"6 1","pages":"910-919"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74216470","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 propose a coarse-fine network (CFN) that exploits multi-level supervisions for keypoint localization. Recently, convolutional neural networks (CNNs)-based methods have achieved great success due to the powerful hierarchical features in CNNs. These methods typically use confidence maps generated from ground-truth keypoint locations as supervisory signals. However, while some keypoints can be easily located with high accuracy, many of them are hard to localize due to appearance ambiguity. Thus, using strict supervision often fails to detect keypoints that are difficult to locate accurately To target this problem, we develop a keypoint localization network composed of several coarse detector branches, each of which is built on top of a feature layer in a CNN, and a fine detector branch built on top of multiple feature layers. We supervise each branch by a specified label map to explicate a certain supervision strictness level. All the branches are unified principally to produce the final accurate keypoint locations. We demonstrate the efficacy, efficiency, and generality of our method on several benchmarks for multiple tasks including bird part localization and human body pose estimation. Especially, our method achieves 72.2% AP on the 2016 COCO Keypoints Challenge dataset, which is an 18% improvement over the winning entry.
{"title":"A Coarse-Fine Network for Keypoint Localization","authors":"Shaoli Huang, Mingming Gong, D. Tao","doi":"10.1109/ICCV.2017.329","DOIUrl":"https://doi.org/10.1109/ICCV.2017.329","url":null,"abstract":"We propose a coarse-fine network (CFN) that exploits multi-level supervisions for keypoint localization. Recently, convolutional neural networks (CNNs)-based methods have achieved great success due to the powerful hierarchical features in CNNs. These methods typically use confidence maps generated from ground-truth keypoint locations as supervisory signals. However, while some keypoints can be easily located with high accuracy, many of them are hard to localize due to appearance ambiguity. Thus, using strict supervision often fails to detect keypoints that are difficult to locate accurately To target this problem, we develop a keypoint localization network composed of several coarse detector branches, each of which is built on top of a feature layer in a CNN, and a fine detector branch built on top of multiple feature layers. We supervise each branch by a specified label map to explicate a certain supervision strictness level. All the branches are unified principally to produce the final accurate keypoint locations. We demonstrate the efficacy, efficiency, and generality of our method on several benchmarks for multiple tasks including bird part localization and human body pose estimation. Especially, our method achieves 72.2% AP on the 2016 COCO Keypoints Challenge dataset, which is an 18% improvement over the winning entry.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"106 1","pages":"3047-3056"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79257455","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}
Bolun Cai, Xian-shun Xu, K. Guo, K. Jia, B. Hu, D. Tao
We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image. The 2D image formed from 3D object in the scene is affected by the intrinsic properties (shape and texture) and the extrinsic property (illumination). Based on a novel structure-preserving measure called local variation deviation, a joint intrinsic-extrinsic prior model is proposed for better representation. Better than conventional Retinex models, the proposed model can preserve the structure information by shape prior, estimate the reflectance with fine details by texture prior, and capture the luminous source by illumination prior. Experimental results demonstrate the effectiveness of the proposed method on simulated and real data. Compared with the other Retinex algorithms and state-of-the-art algorithms, the proposed model yields better results on both subjective and objective assessments.
{"title":"A Joint Intrinsic-Extrinsic Prior Model for Retinex","authors":"Bolun Cai, Xian-shun Xu, K. Guo, K. Jia, B. Hu, D. Tao","doi":"10.1109/ICCV.2017.431","DOIUrl":"https://doi.org/10.1109/ICCV.2017.431","url":null,"abstract":"We propose a joint intrinsic-extrinsic prior model to estimate both illumination and reflectance from an observed image. The 2D image formed from 3D object in the scene is affected by the intrinsic properties (shape and texture) and the extrinsic property (illumination). Based on a novel structure-preserving measure called local variation deviation, a joint intrinsic-extrinsic prior model is proposed for better representation. Better than conventional Retinex models, the proposed model can preserve the structure information by shape prior, estimate the reflectance with fine details by texture prior, and capture the luminous source by illumination prior. Experimental results demonstrate the effectiveness of the proposed method on simulated and real data. Compared with the other Retinex algorithms and state-of-the-art algorithms, the proposed model yields better results on both subjective and objective assessments.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"529 1","pages":"4020-4029"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83367672","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 tackle the vehicle Re-identification (ReID) problem which is of great importance in urban surveillance and can be used for multiple applications. In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed. With orientation invariant feature embedding, local region features of different orientations can be extracted based on 20 key point locations and can be well aligned and combined. With spatial-temporal regularization, the log-normal distribution is adopted to model the spatial-temporal constraints and the retrieval results can be refined. Experiments are conducted on public vehicle ReID datasets and our proposed method achieves state-of-the-art performance. Investigations of the proposed framework is conducted, including the landmark regressor and comparisons with attention mechanism. Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements.
{"title":"Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-identification","authors":"Zhongdao Wang, Luming Tang, Xihui Liu, Zhuliang Yao, Shuai Yi, Jing Shao, Junjie Yan, Shengjin Wang, Hongsheng Li, Xiaogang Wang","doi":"10.1109/ICCV.2017.49","DOIUrl":"https://doi.org/10.1109/ICCV.2017.49","url":null,"abstract":"In this paper, we tackle the vehicle Re-identification (ReID) problem which is of great importance in urban surveillance and can be used for multiple applications. In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed. With orientation invariant feature embedding, local region features of different orientations can be extracted based on 20 key point locations and can be well aligned and combined. With spatial-temporal regularization, the log-normal distribution is adopted to model the spatial-temporal constraints and the retrieval results can be refined. Experiments are conducted on public vehicle ReID datasets and our proposed method achieves state-of-the-art performance. Investigations of the proposed framework is conducted, including the landmark regressor and comparisons with attention mechanism. Both the orientation invariant feature embedding and the spatio-temporal regularization achieve considerable improvements.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"29 1","pages":"379-387"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82241690","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 develop a modified differential Structure from Motion (SfM) algorithm that can estimate relative pose from two consecutive frames despite of Rolling Shutter (RS) artifacts. In particular, we show that under constant velocity assumption, the errors induced by the rolling shutter effect can be easily rectified by a linear scaling operation on each optical flow. We further propose a 9-point algorithm to recover the relative pose of a rolling shutter camera that undergoes constant acceleration motion. We demonstrate that the dense depth maps recovered from the relative pose of the RS camera can be used in a RS-aware warping for image rectification to recover high-quality Global Shutter (GS) images. Experiments on both synthetic and real RS images show that our RS-aware differential SfM algorithm produces more accurate results on relative pose estimation and 3D reconstruction from images distorted by RS effect compared to standard SfM algorithms that assume a GS camera model. We also demonstrate that our RS-aware warping for image rectification method outperforms state-of-the-art commercial software products, i.e. Adobe After Effects and Apple Imovie, at removing RS artifacts.
在本文中，我们开发了一种改进的运动微分结构(SfM)算法，该算法可以在滚动快门(RS)伪影的情况下从两个连续帧中估计相对姿态。特别是，我们证明了在恒定速度假设下，滚动快门效应引起的误差可以很容易地通过对每个光流进行线性缩放操作来纠正。我们进一步提出了一种9点算法来恢复恒定加速度运动下卷帘式相机的相对姿态。我们证明了从RS相机的相对姿态恢复的密集深度图可以用于RS感知的图像校正，以恢复高质量的全局快门(GS)图像。在合成和真实RS图像上的实验表明，与假设GS相机模型的标准SfM算法相比，我们的RS感知差分SfM算法在被RS影响的图像的相对姿态估计和3D重建方面产生了更准确的结果。我们还证明，我们的图像校正方法的RS感知翘曲优于最先进的商业软件产品，即Adobe After Effects和Apple Imovie，在去除RS伪影。
{"title":"Rolling-Shutter-Aware Differential SfM and Image Rectification","authors":"Bingbing Zhuang, L. Cheong, Gim Hee Lee","doi":"10.1109/ICCV.2017.108","DOIUrl":"https://doi.org/10.1109/ICCV.2017.108","url":null,"abstract":"In this paper, we develop a modified differential Structure from Motion (SfM) algorithm that can estimate relative pose from two consecutive frames despite of Rolling Shutter (RS) artifacts. In particular, we show that under constant velocity assumption, the errors induced by the rolling shutter effect can be easily rectified by a linear scaling operation on each optical flow. We further propose a 9-point algorithm to recover the relative pose of a rolling shutter camera that undergoes constant acceleration motion. We demonstrate that the dense depth maps recovered from the relative pose of the RS camera can be used in a RS-aware warping for image rectification to recover high-quality Global Shutter (GS) images. Experiments on both synthetic and real RS images show that our RS-aware differential SfM algorithm produces more accurate results on relative pose estimation and 3D reconstruction from images distorted by RS effect compared to standard SfM algorithms that assume a GS camera model. We also demonstrate that our RS-aware warping for image rectification method outperforms state-of-the-art commercial software products, i.e. Adobe After Effects and Apple Imovie, at removing RS artifacts.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"46 1","pages":"948-956"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80996521","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 addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum ranks of the corresponding local patches with different orientations in gradient domain. Such an approach is motivated by the theoretical analysis which reveals the connection between the rank of a local patch blurred by a defocus-blur kernel and the blur amount by the kernel. After the amounts of defocus blur at edge locations are obtained, a complete defocus map is generated by a standard propagation procedure. The proposed method is extensively evaluated on real image datasets, and the experimental results show its superior performance to existing approaches.
{"title":"Estimating Defocus Blur via Rank of Local Patches","authors":"Guodong Xu, Yuhui Quan, Hui Ji","doi":"10.1109/ICCV.2017.574","DOIUrl":"https://doi.org/10.1109/ICCV.2017.574","url":null,"abstract":"This paper addresses the problem of defocus map estimation from a single image. We present a fast yet effective approach to estimate the spatially varying amounts of defocus blur at edge locations, which is based on the maximum ranks of the corresponding local patches with different orientations in gradient domain. Such an approach is motivated by the theoretical analysis which reveals the connection between the rank of a local patch blurred by a defocus-blur kernel and the blur amount by the kernel. After the amounts of defocus blur at edge locations are obtained, a complete defocus map is generated by a standard propagation procedure. The proposed method is extensively evaluated on real image datasets, and the experimental results show its superior performance to existing approaches.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"22 1","pages":"5381-5389"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83210700","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}
Low-rank and sparse representation based methods have attracted wide attention in background subtraction and moving object detection, where moving objects in the scene are modeled as pixel-wise sparse outliers. Since in real scenarios moving objects are also structurally sparse, recently researchers have attempted to extract moving objects using structured sparse outliers. Although existing methods with structured sparsity-inducing norms produce promising results, they are still vulnerable to various illumination changes that frequently occur in real environments, specifically for time-lapse image sequences where assumptions about sparsity between images such as group sparsity are not valid. In this paper, we first introduce a prior map obtained by illumination invariant representation of images. Next, we propose a low-rank and invariant sparse decomposition using the prior map to detect moving objects under significant illumination changes. Experiments on challenging benchmark datasets demonstrate the superior performance of our proposed method under complex illumination changes.
{"title":"Moving Object Detection in Time-Lapse or Motion Trigger Image Sequences Using Low-Rank and Invariant Sparse Decomposition","authors":"M. Shakeri, Hong Zhang","doi":"10.1109/ICCV.2017.548","DOIUrl":"https://doi.org/10.1109/ICCV.2017.548","url":null,"abstract":"Low-rank and sparse representation based methods have attracted wide attention in background subtraction and moving object detection, where moving objects in the scene are modeled as pixel-wise sparse outliers. Since in real scenarios moving objects are also structurally sparse, recently researchers have attempted to extract moving objects using structured sparse outliers. Although existing methods with structured sparsity-inducing norms produce promising results, they are still vulnerable to various illumination changes that frequently occur in real environments, specifically for time-lapse image sequences where assumptions about sparsity between images such as group sparsity are not valid. In this paper, we first introduce a prior map obtained by illumination invariant representation of images. Next, we propose a low-rank and invariant sparse decomposition using the prior map to detect moving objects under significant illumination changes. Experiments on challenging benchmark datasets demonstrate the superior performance of our proposed method under complex illumination changes.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"27 1","pages":"5133-5141"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78837942","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}
Gerhard Neuhold, Tobias Ollmann, S. R. Bulò, P. Kontschieder
The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes. Annotation is performed in a dense and fine-grained style by using polygons for delineating individual objects. Our dataset is 5× larger than the total amount of fine annotations for Cityscapes and contains images from all around the world, captured at various conditions regarding weather, season and daytime. Images come from different imaging devices (mobile phones, tablets, action cameras, professional capturing rigs) and differently experienced photographers. In such a way, our dataset has been designed and compiled to cover diversity, richness of detail and geographic extent. As default benchmark tasks, we define semantic image segmentation and instance-specific image segmentation, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding.
{"title":"The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes","authors":"Gerhard Neuhold, Tobias Ollmann, S. R. Bulò, P. Kontschieder","doi":"10.1109/ICCV.2017.534","DOIUrl":"https://doi.org/10.1109/ICCV.2017.534","url":null,"abstract":"The Mapillary Vistas Dataset is a novel, large-scale street-level image dataset containing 25000 high-resolution images annotated into 66 object categories with additional, instance-specific labels for 37 classes. Annotation is performed in a dense and fine-grained style by using polygons for delineating individual objects. Our dataset is 5× larger than the total amount of fine annotations for Cityscapes and contains images from all around the world, captured at various conditions regarding weather, season and daytime. Images come from different imaging devices (mobile phones, tablets, action cameras, professional capturing rigs) and differently experienced photographers. In such a way, our dataset has been designed and compiled to cover diversity, richness of detail and geographic extent. As default benchmark tasks, we define semantic image segmentation and instance-specific image segmentation, aiming to significantly further the development of state-of-the-art methods for visual road-scene understanding.","PeriodicalId":6559,"journal":{"name":"2017 IEEE International Conference on Computer Vision (ICCV)","volume":"66 1","pages":"5000-5009"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82706596","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：