2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第9页

RCP: Recurrent Closest Point for Point Cloud RCP:点云的循环最近点

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.00804

Xiaodong Gu, Chengzhou Tang, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Ping Tan

{"title":"RCP: Recurrent Closest Point for Point Cloud","authors":"Xiaodong Gu, Chengzhou Tang, Weihao Yuan, Zuozhuo Dai, Siyu Zhu, Ping Tan","doi":"10.1109/CVPR52688.2022.00804","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00804","url":null,"abstract":"3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow. However, these methods are limited by the fact that it is difficult to define a search window on point clouds because of the irregular data structure. In this paper, we avoid this irregularity by a simple yet effective method. We decompose the problem into two interlaced stages, where the 3D flows are optimized point-wisely at the first stage and then globally regularized in a recurrent network at the second stage. Therefore, the recurrent network only receives the regular point-wise information as the input. In the experiments, we evaluate the proposed method on both the 3D scene flow estimation and the point cloud registration task. For 3D scene flow estimation, we make comparisons on the widely used FlyingThings3D [32] and KITTI [33] datasets. For point cloud registration, we follow previous works and evaluate the data pairs with large pose and partially overlapping from ModelNet40 [65]. The results show that our method outperforms the previous method and achieves a new state-of-the-art performance on both 3D scene flow estimation and point cloud registration, which demonstrates the superiority of the proposed zero-order method on irregular point cloud data. Our source code is available at https://github.com/gxd1994/RCP.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129145767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Task Decoupled Framework for Reference-based Super-Resolution 基于引用的超分辨率任务解耦框架

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.00584

Yixuan Huang, Xiaoyun Zhang, Y. Fu, Siheng Chen, Ya Zhang, Yanfeng Wang, Dazhi He

{"title":"Task Decoupled Framework for Reference-based Super-Resolution","authors":"Yixuan Huang, Xiaoyun Zhang, Y. Fu, Siheng Chen, Ya Zhang, Yanfeng Wang, Dazhi He","doi":"10.1109/CVPR52688.2022.00584","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00584","url":null,"abstract":"Reference-based super-resolution(RefSR) has achieved impressive progress on the recovery of high-frequency details thanks to an additional reference high-resolution(HR) image input. Although the superiority compared with Single-Image Super-Resolution(SISR), existing RefSR methods easily result in the reference-underuse issue and the reference-misuse as shown in Fig. I. In this work, we deeply investigate the cause of the two issues and further propose a novel framework to mitigate them. Our studies find that the issues are mostly due to the improper coupled framework design of current methods. Those methods conduct the super-resolution task of the input low-resolution(LR) image and the texture transfer task from the reference image together in one module, easily introducing the interference between LR and reference features. Inspired by this finding, we propose a novel framework, which decouples the two tasks of RefSR, eliminating the interference between the LR image and the reference image. The super-resolution task upsamples the LR image leveraging only the LR image itself. The texture transfer task extracts and transfers abundant textures from the reference image to the coarsely upsampled result of the super-resolution task. Extensive experiments demonstrate clear improvements in both quantitative and qualitative evaluations over state-of-the-art methods.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122338398","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Learning to Detect Scene Landmarks for Camera Localization 学习检测场景地标相机定位

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.01085

Tien Do, O. Mikšík, Joseph DeGol, Hyunjong Park, Sudipta N. Sinha

{"title":"Learning to Detect Scene Landmarks for Camera Localization","authors":"Tien Do, O. Mikšík, Joseph DeGol, Hyunjong Park, Sudipta N. Sinha","doi":"10.1109/CVPR52688.2022.01085","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01085","url":null,"abstract":"Modern camera localization methods that use image retrieval, feature matching, and 3D structure-based pose estimation require long-term storage of numerous scene images or a vast amount of image features. This can make them unsuitable for resource constrained VR/AR devices and also raises serious privacy concerns. We present a new learned camera localization technique that eliminates the need to store features or a detailed 3D point cloud. Our key idea is to implicitly encode the appearance of a sparse yet salient set of 3D scene points into a convolutional neural network (CNN) that can detect these scene points in query images whenever they are visible. We refer to these points as scene landmarks. We also show that a CNN can be trained to regress bearing vectors for such landmarks even when they are not within the camera's field-of-view. We demonstrate that the predicted landmarks yield accurate pose estimates and that our method outperforms DSAC*, the state-of-the-art in learned localization. Furthermore, extending HLoc (an accurate method) by combining its correspondences with our predictions boosts its accuracy even further.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123725509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Mutual Quantization for Cross-Modal Search with Noisy Labels 带噪声标签的跨模态搜索的相互量化

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.00740

Erkun Yang, Dongren Yao, Tongliang Liu, Cheng Deng

{"title":"Mutual Quantization for Cross-Modal Search with Noisy Labels","authors":"Erkun Yang, Dongren Yao, Tongliang Liu, Cheng Deng","doi":"10.1109/CVPR52688.2022.00740","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00740","url":null,"abstract":"Deep cross-modal hashing has become an essential tool for supervised multimodal search. These models tend to be optimized with large, curated multimodal datasets, where most labels have been manually verified. Unfortunately, in many scenarios, such accurate labeling may not be avail-able. In contrast, datasets with low-quality annotations may be acquired, which inevitably introduce numerous mis-takes or label noise and therefore degrade the search per-formance. To address the challenge, we present a general robust cross-modal hashing framework to correlate distinct modalities and combat noisy labels simultaneously. More specifically, we propose a proxy-based contrastive (PC) loss to mitigate the gap between different modalities and train networks for different modalities Jointly with small-loss samples that are selected with the PC loss and a mu-tual quantization loss. The small-loss sample selection from such Joint loss can help choose confident examples to guide the model training, and the mutual quantization loss can maximize the agreement between different modalities and is beneficial to improve the effectiveness of sample selection. Experiments on three widely-used multimodal datasets show that our method significantly outperforms existing state-of-the-arts.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132879394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Semantic-Aware Auto-Encoders for Self-supervised Representation Learning 用于自监督表示学习的语义感知自编码器

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.00944

Guangrun Wang, Yansong Tang, Liang Lin, Philip H. S. Torr

{"title":"Semantic-Aware Auto-Encoders for Self-supervised Representation Learning","authors":"Guangrun Wang, Yansong Tang, Liang Lin, Philip H. S. Torr","doi":"10.1109/CVPR52688.2022.00944","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.00944","url":null,"abstract":"The resurgence of unsupervised learning can be attributed to the remarkable progress of self-supervised learning, which includes generative $(mathcal{G})$ and discriminative $(mathcal{D})$ models. In computer vision, the mainstream self-supervised learning algorithms are $mathcal{D}$ models. However, designing a $mathcal{D}$ model could be over-complicated; also, some studies hinted that a $mathcal{D}$ model might not be as general and interpretable as a $mathcal{G}$ model. In this paper, we switch from $mathcal{D}$ models to $mathcal{G}$ models using the classical auto-encoder $(AE)$. Note that a vanilla $mathcal{G}$ model was far less efficient than a $mathcal{D}$ model in self-supervised computer vision tasks, as it wastes model capability on overfitting semantic-agnostic high-frequency details. Inspired by perceptual learning that could use cross-view learning to perceive concepts and semantics11Following [26], we refer to semantics as visual concepts, e.g., a semantic-ware model indicates the model can perceive visual concepts, and the learned features are efficient in object recognition, detection, etc., we propose a novel $AE$ that could learn semantic-aware representation via cross-view image reconstruction. We use one view of an image as the input and another view of the same image as the reconstruction target. This kind of $AE$ has rarely been studied before, and the optimization is very difficult. To enhance learning ability and find a feasible solution, we propose a semantic aligner that uses geometric transformation knowledge to align the hidden code of $AE$ to help optimization. These techniques significantly improve the representation learning ability of $AE$ and make selfsupervised learning with $mathcal{G}$ models possible. Extensive experiments on many large-scale benchmarks (e.g., ImageNet, COCO 2017, and SYSU-30k) demonstrate the effectiveness of our methods. Code is available at https://github.com/wanggrun/Semantic-Aware-AE.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132987467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Bayesian Invariant Risk Minimization 贝叶斯不变风险最小化

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.01555

Yong Lin, Hanze Dong, Hao Wang, Tong Zhang

{"title":"Bayesian Invariant Risk Minimization","authors":"Yong Lin, Hanze Dong, Hao Wang, Tong Zhang","doi":"10.1109/CVPR52688.2022.01555","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.01555","url":null,"abstract":"Generalization under distributional shift is an open challenge for machine learning. Invariant Risk Minimization (IRM) is a promising framework to tackle this issue by extracting invariant features. However, despite the potential and popularity of IRM, recent works have reported negative results of it on deep models. We argue that the failure can be primarily attributed to deep models' tendency to overfit the data. Specifically, our theoretical analysis shows that IRM degenerates to empirical risk minimization (ERM) when overfitting occurs. Our empirical evidence also provides supports: IRM methods that work well in typical settings significantly deteriorate even if we slightly enlarge the model size or lessen the training data. To alleviate this issue, we propose Bayesian Invariant Risk Min-imization (BIRM) by introducing Bayesian inference into the IRM. The key motivation is to estimate the penalty of IRM based on the posterior distribution of classifiers (as opposed to a single classifier), which is much less prone to overfitting. Extensive experimental results on four datasets demonstrate that BIRM consistently outperforms the existing IRM baselines significantly.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131013194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 33

Boosting View Synthesis with Residual Transfer 用残余转移增强视图合成

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.01914

Xuejian Rong, Jia-Bin Huang, Ayush Saraf, Changil Kim, J. Kopf

引用次数: 1

Effective conditioned and composed image retrieval combining CLIP-based features 结合基于clip特征的有效条件和组合图像检索

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.02080

Alberto Baldrati, M. Bertini, Tiberio Uricchio, A. Bimbo

{"title":"Effective conditioned and composed image retrieval combining CLIP-based features","authors":"Alberto Baldrati, M. Bertini, Tiberio Uricchio, A. Bimbo","doi":"10.1109/CVPR52688.2022.02080","DOIUrl":"https://doi.org/10.1109/CVPR52688.2022.02080","url":null,"abstract":"Conditioned and composed image retrieval extend CBIR systems by combining a query image with an additional text that expresses the intent of the user, describing additional requests w.r.t. the visual content of the query image. This type of search is interesting for e-commerce applications, e.g. to develop interactive multimodal searches and chat-bots. In this demo, we present an interactive system based on a combiner network, trained using contrastive learning, that combines visual and textual features obtained from the OpenAI CLIP network to address conditioned CBIR. The system can be used to improve e-shop search engines. For example, considering the fashion domain it lets users search for dresses, shirts and toptees using a candidate start image and expressing some visual differences w.r.t. its visual con-tent, e.g. asking to change color, pattern or shape. The pro-posed network obtains state-of-the-art performance on the FashionIQ dataset and on the more recent CIRR dataset, showing its applicability to the fashion domain for conditioned retrieval, and to more generic content considering the more general task of composed image retrieval.","PeriodicalId":355552,"journal":{"name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127914155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 45

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.01636

Minh-Hieu Phan, The-Anh Ta, S. L. Phung, Long Tran-Thanh, A. Bouzerdoum

引用次数: 20

FashionVLP: Vision Language Transformer for Fashion Retrieval with Feedback 时尚vlp:基于反馈的时尚检索视觉语言转换器

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2022-06-01 DOI: 10.1109/CVPR52688.2022.01371

Sonam Goenka, Zhao-Heng Zheng, Ayush Jaiswal, Rakesh Chada, Yuehua Wu, Varsha Hedau, P. Natarajan

引用次数: 40