Occluded person re-identification (ReID) aims at re-identifying occluded pedestrians from occluded or holistic images taken across multiple cameras. Current state-of-the-art (SOTA) occluded ReID models rely on some auxiliary modules, including pose estimation, feature pyramid and graph matching modules, to learn multi-scale and/or part-level features to tackle the occlusion challenges. This unfortunately leads to complex ReID models that (i) fail to generalize to challenging occlusions of diverse appearance, shape or size, and (ii) become ineffective in handling non-occluded pedestrians. However, real-world ReID applications typically have highly diverse occlusions and involve a hybrid of occluded and non-occluded pedestrians. To address these two issues, we introduce a novel ReID model that learns discriminative single-scale global-level pedestrian features by enforcing a novel exponentially sensitive yet bounded distance loss on occlusion-based augmented data. We show for the first time that learning single-scale global features without using these auxiliary modules is able to outperform the SOTA multi-scale and/or part-level feature-based models. Further, our simple model can achieve new SOTA performance in both occluded and non-occluded ReID, as shown by extensive results on three occluded and two general ReID benchmarks. Additionally, we create a large-scale occluded person ReID dataset with various occlusions in different scenes, which is significantly larger and contains more diverse occlusions and pedestrian dressings than existing occluded ReID datasets, providing a more faithful occluded ReID benchmark. The dataset is available at: https://git.io/OPReID
{"title":"Occluded Person Re-Identification with Single-scale Global Representations","authors":"Cheng Yan, Guansong Pang, J. Jiao, Xiaolong Bai, Xuetao Feng, Chunhua Shen","doi":"10.1109/ICCV48922.2021.01166","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01166","url":null,"abstract":"Occluded person re-identification (ReID) aims at re-identifying occluded pedestrians from occluded or holistic images taken across multiple cameras. Current state-of-the-art (SOTA) occluded ReID models rely on some auxiliary modules, including pose estimation, feature pyramid and graph matching modules, to learn multi-scale and/or part-level features to tackle the occlusion challenges. This unfortunately leads to complex ReID models that (i) fail to generalize to challenging occlusions of diverse appearance, shape or size, and (ii) become ineffective in handling non-occluded pedestrians. However, real-world ReID applications typically have highly diverse occlusions and involve a hybrid of occluded and non-occluded pedestrians. To address these two issues, we introduce a novel ReID model that learns discriminative single-scale global-level pedestrian features by enforcing a novel exponentially sensitive yet bounded distance loss on occlusion-based augmented data. We show for the first time that learning single-scale global features without using these auxiliary modules is able to outperform the SOTA multi-scale and/or part-level feature-based models. Further, our simple model can achieve new SOTA performance in both occluded and non-occluded ReID, as shown by extensive results on three occluded and two general ReID benchmarks. Additionally, we create a large-scale occluded person ReID dataset with various occlusions in different scenes, which is significantly larger and contains more diverse occlusions and pedestrian dressings than existing occluded ReID datasets, providing a more faithful occluded ReID benchmark. The dataset is available at: https://git.io/OPReID","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"4 1","pages":"11855-11864"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74096042","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}
Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00535
Zhirui Dai, Yue-Ren Jiang, Yi Li, Bo Liu, Antoni B. Chan, Nuno Vasconcelos
Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas, with wide field-of-view cameras, is considered. A dataset of crowd scenes with people annotations under a bird’s eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated. BEV-Net combines detection of head and feet locations, camera pose estimation, a differentiable homography module to map image into BEV coordinates, and geometric reasoning to produce a BEV map of the people locations in the scene. Experiments on complex crowded scenes demonstrate the power of the approach and show superior performance over baselines derived from methods in the literature. Applications of interest for public health decision makers are finally discussed. Datasets, code and pretrained models are publicly available at GitHub1.
{"title":"BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning","authors":"Zhirui Dai, Yue-Ren Jiang, Yi Li, Bo Liu, Antoni B. Chan, Nuno Vasconcelos","doi":"10.1109/ICCV48922.2021.00535","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00535","url":null,"abstract":"Social distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas, with wide field-of-view cameras, is considered. A dataset of crowd scenes with people annotations under a bird’s eye view (BEV) and ground truth for metric distances is introduced, and several measures for the evaluation of social distance detection systems are proposed. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated. BEV-Net combines detection of head and feet locations, camera pose estimation, a differentiable homography module to map image into BEV coordinates, and geometric reasoning to produce a BEV map of the people locations in the scene. Experiments on complex crowded scenes demonstrate the power of the approach and show superior performance over baselines derived from methods in the literature. Applications of interest for public health decision makers are finally discussed. Datasets, code and pretrained models are publicly available at GitHub1.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"47 47 1","pages":"5381-5391"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77050331","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}
Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00626
Zhicong Huang, Xue-mei Hu, Zhou Xue, Weizhu Xu, Tao Yue
Light field images contain both angular and spatial information of captured light rays. The rich information of light fields enables straightforward disparity recovery capability but demands high computational cost as well. In this paper, we design a lightweight disparity estimation model with physical-based multi-disparity-scale cost volume aggregation for fast disparity estimation. By introducing a sub-network of edge guidance, we significantly improve the recovery of geometric details near edges and improve the overall performance. We test the proposed model extensively on both synthetic and real-captured datasets, which provide both densely and sparsely sampled light fields. Finally, we significantly reduce computation cost and GPU memory consumption, while achieving comparable performance with state-of-the-art disparity estimation methods for light fields. Our source code is available at https://github.com/zcong17huang/FastLFnet.
{"title":"Fast Light-field Disparity Estimation with Multi-disparity-scale Cost Aggregation","authors":"Zhicong Huang, Xue-mei Hu, Zhou Xue, Weizhu Xu, Tao Yue","doi":"10.1109/ICCV48922.2021.00626","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00626","url":null,"abstract":"Light field images contain both angular and spatial information of captured light rays. The rich information of light fields enables straightforward disparity recovery capability but demands high computational cost as well. In this paper, we design a lightweight disparity estimation model with physical-based multi-disparity-scale cost volume aggregation for fast disparity estimation. By introducing a sub-network of edge guidance, we significantly improve the recovery of geometric details near edges and improve the overall performance. We test the proposed model extensively on both synthetic and real-captured datasets, which provide both densely and sparsely sampled light fields. Finally, we significantly reduce computation cost and GPU memory consumption, while achieving comparable performance with state-of-the-art disparity estimation methods for light fields. Our source code is available at https://github.com/zcong17huang/FastLFnet.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"6300-6309"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77120881","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}
Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00723
Dahye Kim, Byung-Woo Hong
We present an image segmentation algorithm that is developed in an unsupervised deep learning framework. The delineation of object boundaries often fails due to the nuisance factors such as illumination changes and occlusions. Thus, we initially propose an unsupervised image decomposition algorithm to obtain an intrinsic representation that is robust with respect to undesirable bias fields based on a multiplicative image model. The obtained intrinsic image is subsequently provided to an unsupervised segmentation procedure that is developed based on a piecewise smooth model. The segmentation model is further designed to incorporate a geometric constraint imposed in the generative adversarial network framework where the discrepancy between the distribution of partitioning functions and the distribution of prior shapes is minimized. We demonstrate the effectiveness and robustness of the proposed algorithm in particular with bias fields and occlusions using simple yet illustrative synthetic examples and a benchmark dataset for image segmentation.
{"title":"Unsupervised Segmentation incorporating Shape Prior via Generative Adversarial Networks","authors":"Dahye Kim, Byung-Woo Hong","doi":"10.1109/ICCV48922.2021.00723","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00723","url":null,"abstract":"We present an image segmentation algorithm that is developed in an unsupervised deep learning framework. The delineation of object boundaries often fails due to the nuisance factors such as illumination changes and occlusions. Thus, we initially propose an unsupervised image decomposition algorithm to obtain an intrinsic representation that is robust with respect to undesirable bias fields based on a multiplicative image model. The obtained intrinsic image is subsequently provided to an unsupervised segmentation procedure that is developed based on a piecewise smooth model. The segmentation model is further designed to incorporate a geometric constraint imposed in the generative adversarial network framework where the discrepancy between the distribution of partitioning functions and the distribution of prior shapes is minimized. We demonstrate the effectiveness and robustness of the proposed algorithm in particular with bias fields and occlusions using simple yet illustrative synthetic examples and a benchmark dataset for image segmentation.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"38 1","pages":"7304-7314"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77645751","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}
Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00682
Da Chen, L. Cohen, J. Mirebeau, X. Tai
The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit the image features in conjunction with geometric regularization terms (such as curve length or elastica length) for computing geodesic paths. In this paper, we consider a more complicated problem: finding simple and closed geodesic curves which are imposed a convexity shape prior. The proposed approach relies on an orientation-lifting strategy, by which a planar curve can be mapped to an high-dimensional orientation space. The convexity shape prior serves as a constraint for the construction of local metrics. The geodesic curves in the lifted space then can be efficiently computed through the fast marching method. In addition, we introduce a way to incorporate region-based homogeneity features into the proposed geodesic model so as to solve the region-based segmentation issues with shape prior constraints.
{"title":"An Elastica Geodesic Approach with Convexity Shape Prior","authors":"Da Chen, L. Cohen, J. Mirebeau, X. Tai","doi":"10.1109/ICCV48922.2021.00682","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00682","url":null,"abstract":"The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit the image features in conjunction with geometric regularization terms (such as curve length or elastica length) for computing geodesic paths. In this paper, we consider a more complicated problem: finding simple and closed geodesic curves which are imposed a convexity shape prior. The proposed approach relies on an orientation-lifting strategy, by which a planar curve can be mapped to an high-dimensional orientation space. The convexity shape prior serves as a constraint for the construction of local metrics. The geodesic curves in the lifted space then can be efficiently computed through the fast marching method. In addition, we introduce a way to incorporate region-based homogeneity features into the proposed geodesic model so as to solve the region-based segmentation issues with shape prior constraints.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"33 1","pages":"6880-6889"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75082018","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-action video recognition is much more challenging due to the requirement to recognize multiple actions co-occurring simultaneously or sequentially. Modeling multi-action relations is beneficial and crucial to understand videos with multiple actions, and actions in a video are usually presented in multiple modalities. In this paper, we propose a novel multi-action relation model for videos, by leveraging both relational graph convolutional networks (GCNs) and video multi-modality. We first build multi-modal GCNs to explore modality-aware multi-action relations, fed by modality-specific action representation as node features, i.e., spatiotemporal features learned by 3D convolutional neural network (CNN), audio and textual embeddings queried from respective feature lexicons. We then joint both multi-modal CNN-GCN models and multi-modal feature representations for learning better relational action predictions. Ablation study, multi-action relation visualization, and boosts analysis, all show efficacy of our multi-modal multi-action relation modeling. Also our method achieves state-of-the-art performance on large-scale multi-action M-MiT benchmark. Our code is made publicly available at https://github.com/zhenglab/multi-action-video.
{"title":"Multi-Modal Multi-Action Video Recognition","authors":"Zhensheng Shi, Ju Liang, Qianqian Li, Haiyong Zheng, Zhaorui Gu, Junyu Dong, Bing Zheng","doi":"10.1109/ICCV48922.2021.01342","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01342","url":null,"abstract":"Multi-action video recognition is much more challenging due to the requirement to recognize multiple actions co-occurring simultaneously or sequentially. Modeling multi-action relations is beneficial and crucial to understand videos with multiple actions, and actions in a video are usually presented in multiple modalities. In this paper, we propose a novel multi-action relation model for videos, by leveraging both relational graph convolutional networks (GCNs) and video multi-modality. We first build multi-modal GCNs to explore modality-aware multi-action relations, fed by modality-specific action representation as node features, i.e., spatiotemporal features learned by 3D convolutional neural network (CNN), audio and textual embeddings queried from respective feature lexicons. We then joint both multi-modal CNN-GCN models and multi-modal feature representations for learning better relational action predictions. Ablation study, multi-action relation visualization, and boosts analysis, all show efficacy of our multi-modal multi-action relation modeling. Also our method achieves state-of-the-art performance on large-scale multi-action M-MiT benchmark. Our code is made publicly available at https://github.com/zhenglab/multi-action-video.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"99 1","pages":"13658-13667"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76585518","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}
Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.01177
Qinqin Zhou, Xiawu Zheng, Liujuan Cao, Bineng Zhong, Teng Xi, Gang Zhang, Errui Ding, Mingliang Xu, Rongrong Ji
Based on the relaxed search space, differential architecture search (DARTS) is efficient in searching for a high-performance architecture. However, the unbalanced competition among operations that have different trainable parameters causes the model collapse. Besides, the inconsistent structures in the search and retraining stages causes cross-stage evaluation to be unstable. In this paper, we call these issues as an operation gap and a structure gap in DARTS. To shrink these gaps, we propose to induce equalized and consistent optimization in differentiable architecture search (EC-DARTS). EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked. Besides, we introduce an induced structural transition to bridge the structure gap between the model structures in the search and retraining stages. Extensive experiments on CIFAR10 and ImageNet demonstrate the effectiveness of our method. Specifically, on CIFAR10, we achieve a test error of 2.39%, while only 0.3 GPU days on NVIDIA TITAN V. On ImageNet, our method achieves a top-1 error of 23.6% under the mobile setting.
{"title":"EC-DARTS: Inducing Equalized and Consistent Optimization into DARTS","authors":"Qinqin Zhou, Xiawu Zheng, Liujuan Cao, Bineng Zhong, Teng Xi, Gang Zhang, Errui Ding, Mingliang Xu, Rongrong Ji","doi":"10.1109/ICCV48922.2021.01177","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01177","url":null,"abstract":"Based on the relaxed search space, differential architecture search (DARTS) is efficient in searching for a high-performance architecture. However, the unbalanced competition among operations that have different trainable parameters causes the model collapse. Besides, the inconsistent structures in the search and retraining stages causes cross-stage evaluation to be unstable. In this paper, we call these issues as an operation gap and a structure gap in DARTS. To shrink these gaps, we propose to induce equalized and consistent optimization in differentiable architecture search (EC-DARTS). EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked. Besides, we introduce an induced structural transition to bridge the structure gap between the model structures in the search and retraining stages. Extensive experiments on CIFAR10 and ImageNet demonstrate the effectiveness of our method. Specifically, on CIFAR10, we achieve a test error of 2.39%, while only 0.3 GPU days on NVIDIA TITAN V. On ImageNet, our method achieves a top-1 error of 23.6% under the mobile setting.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"48 1","pages":"11966-11975"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77026827","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}
Virtual try-on tasks have drawn increased attention. Prior arts focus on tackling this task via warping clothes and fusing the information at the pixel level with the help of semantic segmentation. However, conducting semantic segmentation is time-consuming and easily causes error accumulation over time. Besides, warping the information at the pixel level instead of the feature level limits the performance (e.g., unable to generate different views) and is unstable since it directly demonstrates the results even with a misalignment. In contrast, fusing information at the feature level can be further refined by the convolution to obtain the final results. Based on these assumptions, we propose a co-attention feature-remapping framework, namely FashionMirror, that generates the try-on results according to the driven-pose sequence in two stages. In the first stage, we consider the source human image and the target try-on clothes to predict the removed mask and the try-on clothing mask, which replaces the pre-processed semantic segmentation and reduces the inference time. In the second stage, we first remove the clothes on the source human via the removed mask and warp the clothing features conditioning on the try-on clothing mask to fit the next frame human. Meanwhile, we predict the optical flows from the consecutive 2D poses and warp the source human to the next frame at the feature level. Then, we enhance the clothing features and source human features in every frame to generate realistic try-on results with spatiotemporal smoothness. Both qualitative and quantitative results show that FashionMirror outperforms the state-of-the-art virtual try-on approaches.
{"title":"FashionMirror: Co-attention Feature-remapping Virtual Try-on with Sequential Template Poses","authors":"Chieh-Yun Chen, Ling Lo, Pin-Jui Huang, Hong-Han Shuai, Wen-Huang Cheng","doi":"10.1109/ICCV48922.2021.01355","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01355","url":null,"abstract":"Virtual try-on tasks have drawn increased attention. Prior arts focus on tackling this task via warping clothes and fusing the information at the pixel level with the help of semantic segmentation. However, conducting semantic segmentation is time-consuming and easily causes error accumulation over time. Besides, warping the information at the pixel level instead of the feature level limits the performance (e.g., unable to generate different views) and is unstable since it directly demonstrates the results even with a misalignment. In contrast, fusing information at the feature level can be further refined by the convolution to obtain the final results. Based on these assumptions, we propose a co-attention feature-remapping framework, namely FashionMirror, that generates the try-on results according to the driven-pose sequence in two stages. In the first stage, we consider the source human image and the target try-on clothes to predict the removed mask and the try-on clothing mask, which replaces the pre-processed semantic segmentation and reduces the inference time. In the second stage, we first remove the clothes on the source human via the removed mask and warp the clothing features conditioning on the try-on clothing mask to fit the next frame human. Meanwhile, we predict the optical flows from the consecutive 2D poses and warp the source human to the next frame at the feature level. Then, we enhance the clothing features and source human features in every frame to generate realistic try-on results with spatiotemporal smoothness. Both qualitative and quantitative results show that FashionMirror outperforms the state-of-the-art virtual try-on approaches.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"43 1","pages":"13789-13798"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77093870","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}
Online semantic segmentation on a time series of point cloud frames is an essential task in autonomous driving. Existing models focus on single-frame segmentation, which cannot achieve satisfactory segmentation accuracy and offer unstably flicker among frames. In this paper, we propose a light-weight semantic segmentation framework for largescale point cloud series, called TempNet, which can improve both the accuracy and the stability of existing semantic segmentation models by combining a novel frame aggregation scheme. To be computational cost-efficient, feature extraction and aggregation are only conducted on a small portion of key frames via a temporal feature aggregation (TFA) network using an attentional pooling mechanism, and such enhanced features are propagated to the intermediate non-key frames. To avoid information loss from non-key frames, a partial feature update (PFU) network is designed to partially update the propagated features with the local features extracted on a non-key frame if a large disparity between the two is quickly assessed. As a result, consistent and information-rich features can be obtained for each frame. We implement TempNet on five state-of-the-art (SOTA) point cloud segmentation models and conduct extensive experiments on the SemanticKITTI dataset. Results demonstrate that TempNet outperforms SOTA competitors by wide margins with little extra computational cost.
{"title":"TempNet: Online Semantic Segmentation on Large-scale Point Cloud Series","authors":"Yunsong Zhou, Hongzi Zhu, Chunqin Li, Tiankai Cui, Shan Chang, Minyi Guo","doi":"10.1109/ICCV48922.2021.00703","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00703","url":null,"abstract":"Online semantic segmentation on a time series of point cloud frames is an essential task in autonomous driving. Existing models focus on single-frame segmentation, which cannot achieve satisfactory segmentation accuracy and offer unstably flicker among frames. In this paper, we propose a light-weight semantic segmentation framework for largescale point cloud series, called TempNet, which can improve both the accuracy and the stability of existing semantic segmentation models by combining a novel frame aggregation scheme. To be computational cost-efficient, feature extraction and aggregation are only conducted on a small portion of key frames via a temporal feature aggregation (TFA) network using an attentional pooling mechanism, and such enhanced features are propagated to the intermediate non-key frames. To avoid information loss from non-key frames, a partial feature update (PFU) network is designed to partially update the propagated features with the local features extracted on a non-key frame if a large disparity between the two is quickly assessed. As a result, consistent and information-rich features can be obtained for each frame. We implement TempNet on five state-of-the-art (SOTA) point cloud segmentation models and conduct extensive experiments on the SemanticKITTI dataset. Results demonstrate that TempNet outperforms SOTA competitors by wide margins with little extra computational cost.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"14 1","pages":"7098-7107"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79032589","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}
Pub Date : 2021-10-01DOI: 10.1109/ICCV48922.2021.00563
Donghoon Lee, Onur C. Hamsici, Steven Feng, P. Sharma, Thorsten Gernoth, Apple
We consider the problem of online and real-time registration of partial point clouds obtained from an unseen real-world rigid object without knowing its 3D model. The point cloud is partial as it is obtained by a depth sensor capturing only the visible part of the object from a certain viewpoint. It introduces two main challenges: 1) two partial point clouds do not fully overlap and 2) keypoints tend to be less reliable when the visible part of the object does not have salient local structures. To address these issues, we propose DeepPRO, a keypoint-free and an end-to-end trainable deep neural network. Its core idea is inspired by how humans align two point clouds: we can imagine how two point clouds will look like after the registration based on their shape. To realize the idea, DeepPRO has inputs of two partial point clouds and directly predicts the point-wise location of the aligned point cloud. By preserving the ordering of points during the prediction, we enjoy dense correspondences between input and predicted point clouds when inferring rigid transform parameters. We conduct extensive experiments on the real-world Linemod and synthetic ModelNet40 datasets. In addition, we collect and evaluate on the PRO1k dataset, a large-scale version of Linemod meant to test generalization to real-world scans. Results show that DeepPRO achieves the best accuracy against thirteen strong baseline methods, e.g., 2.2mm ADD on the Linemod dataset, while running 50 fps on mobile devices.
{"title":"DeepPRO: Deep Partial Point Cloud Registration of Objects","authors":"Donghoon Lee, Onur C. Hamsici, Steven Feng, P. Sharma, Thorsten Gernoth, Apple","doi":"10.1109/ICCV48922.2021.00563","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00563","url":null,"abstract":"We consider the problem of online and real-time registration of partial point clouds obtained from an unseen real-world rigid object without knowing its 3D model. The point cloud is partial as it is obtained by a depth sensor capturing only the visible part of the object from a certain viewpoint. It introduces two main challenges: 1) two partial point clouds do not fully overlap and 2) keypoints tend to be less reliable when the visible part of the object does not have salient local structures. To address these issues, we propose DeepPRO, a keypoint-free and an end-to-end trainable deep neural network. Its core idea is inspired by how humans align two point clouds: we can imagine how two point clouds will look like after the registration based on their shape. To realize the idea, DeepPRO has inputs of two partial point clouds and directly predicts the point-wise location of the aligned point cloud. By preserving the ordering of points during the prediction, we enjoy dense correspondences between input and predicted point clouds when inferring rigid transform parameters. We conduct extensive experiments on the real-world Linemod and synthetic ModelNet40 datasets. In addition, we collect and evaluate on the PRO1k dataset, a large-scale version of Linemod meant to test generalization to real-world scans. Results show that DeepPRO achieves the best accuracy against thirteen strong baseline methods, e.g., 2.2mm ADD on the Linemod dataset, while running 50 fps on mobile devices.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"18 1","pages":"5663-5672"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75529339","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：