2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)最新文献_第4页

FastSwap: A Lightweight One-Stage Framework for Real-Time Face Swapping FastSwap:用于实时人脸交换的轻量级单阶段框架

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00355

Sahng-Min Yoo, Taehyean Choi, Jae-Woo Choi, Jong-Hwan Kim

引用次数: 0

Multi-Frame Attention with Feature-Level Warping for Drone Crowd Tracking 多帧关注与特征级翘曲无人机人群跟踪

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00171

Takanori Asanomi, Kazuya Nishimura, Ryoma Bise

{"title":"Multi-Frame Attention with Feature-Level Warping for Drone Crowd Tracking","authors":"Takanori Asanomi, Kazuya Nishimura, Ryoma Bise","doi":"10.1109/WACV56688.2023.00171","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00171","url":null,"abstract":"Drone crowd tracking has various applications such as crowd management and video surveillance. Unlike in general multi-object tracking, the size of the objects to be tracked are small, and the ground truth is given by a point-level annotation, which has no region information. This causes the lack of discriminative features for finding the same objects from many similar objects. Thus, similarity-based tracking techniques, which are widely used for multi-object tracking with bounding-box, are difficult to use. To deal with this problem, we take into account the temporal context of the local area. To aggregate temporal context in a local area, we propose a multi-frame attention with feature-level warping. The feature-level warping can align the features of the same object in multiple frames, and then multi-frame attention can effectively aggregate the temporal context from the warped features. The experimental results show the effectiveness of our method. Our method outperformed the state-of-the-art method in DroneCrowd dataset. The code is publicly available in https://github.com/asanomitakanori/mfa-feature-warping.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121862061","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: 1

Separating Partially-Polarized Diffuse and Specular Reflection Components under Unpolarized Light Sources 在非偏振光源下分离部分偏振漫反射和镜面反射分量

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00258

Soma Kajiyama, Taihe Piao, Ryo Kawahara, Takahiro Okabe

{"title":"Separating Partially-Polarized Diffuse and Specular Reflection Components under Unpolarized Light Sources","authors":"Soma Kajiyama, Taihe Piao, Ryo Kawahara, Takahiro Okabe","doi":"10.1109/WACV56688.2023.00258","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00258","url":null,"abstract":"Separating diffuse and specular reflection components observed on an object surface is important for preprocessing of various computer vision techniques. Conventionally, diffuse-specular separation based on the polarimetric and color clues assumes that the diffuse/specular reflection components are unpolarized/partially polarized under unpolarized light sources. However, the diffuse reflection component is partially polarized in fact, because the diffuse reflectance is maximal when the polarization direction is parallel to the outgoing plane. Accordingly, we propose a method for separating partially-polarized diffuse and specular reflection components on the basis of the polarization reflection model and the dichromatic reflection model. In particular, our method enables us not only to achieve diffuse-specular separation but also to estimate the polarimetric properties of the object surface from a single color polarization image. We experimentally confirmed that our method performs better than the method assuming unpolarized diffuse reflection components.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124478375","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: 0

Nested Deformable Multi-head Attention for Facial Image Inpainting 嵌套可变形多头面部图像绘制注意事项

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00602

Shruti S. Phutke, S. Murala

{"title":"Nested Deformable Multi-head Attention for Facial Image Inpainting","authors":"Shruti S. Phutke, S. Murala","doi":"10.1109/WACV56688.2023.00602","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00602","url":null,"abstract":"Extracting adequate contextual information is an important aspect of any image inpainting method. To achieve this, ample image inpainting methods are available that aim to focus on large receptive fields. Recent advancements in the deep learning field with the introduction of transformers for image inpainting paved the way toward plausible results. Stacking multiple transformer blocks in a single layer causes the architecture to become computationally complex. In this context, we propose a novel lightweight architecture with a nested deformable attention-based transformer layer for feature fusion. The nested attention helps the network to focus on long-term dependencies from encoder and decoder features. Also, multi-head attention consisting of a deformable convolution is proposed to delve into the diverse receptive fields. With the advantage of nested and deformable attention, we propose a lightweight architecture for facial image inpainting. The results comparison on Celeb HQ [25] dataset using known (NVIDIA) and unknown (QD-IMD) masks and Places2 [57] dataset with NVIDIA masks along with extensive ablation study prove the superiority of the proposed approach for image inpainting tasks. The code is available at: https://github.com/shrutiphutke/NDMA_Facial_Inpainting.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129083545","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: 1

Training Auxiliary Prototypical Classifiers for Explainable Anomaly Detection in Medical Image Segmentation 医学图像分割中可解释异常检测的辅助原型分类器训练

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00265

Wonwoong Cho, Jeonghoon Park, J. Choo

{"title":"Training Auxiliary Prototypical Classifiers for Explainable Anomaly Detection in Medical Image Segmentation","authors":"Wonwoong Cho, Jeonghoon Park, J. Choo","doi":"10.1109/WACV56688.2023.00265","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00265","url":null,"abstract":"Machine learning-based algorithms using fully convolutional networks (FCNs) have been a promising option for medical image segmentation. However, such deep networks silently fail if input samples are drawn far from the training data distribution, thus causing critical problems in automatic data processing pipelines. To overcome such out-of-distribution (OoD) problems, we propose a novel OoD score formulation and its regularization strategy by applying an auxiliary add-on classifier to an intermediate layer of an FCN, where the auxiliary module is helfpul for analyzing the encoder output features by taking their class information into account. Our regularization strategy train the module along with the FCN via the principle of outlier exposure so that our model can be trained to distinguish OoD samples from normal ones without modifying the original network architecture. Our extensive experiment results demonstrate that the proposed approach can successfully conduct effective OoD detection without loss of segmentation performance. In addition, our module can provide reasonable explanation maps along with OoD scores, which can enable users to analyze the reliability of predictions.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130852698","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: 3

3D-SpLineNet: 3D Traffic Line Detection using Parametric Spline Representations 3D- splinenet:使用参数样条表示的3D交通线检测

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00067

M. Pittner, A. Condurache, J. Janai

{"title":"3D-SpLineNet: 3D Traffic Line Detection using Parametric Spline Representations","authors":"M. Pittner, A. Condurache, J. Janai","doi":"10.1109/WACV56688.2023.00067","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00067","url":null,"abstract":"Monocular 3D traffic line detection jointly tackles the detection of lane markings and regression of their 3D location. The greatest challenge is the exact estimation of various line shapes in the world, which highly depends on the chosen representation. While anchor-based and grid-based line representations have been proposed, all suffer from the same limitation, the necessity of discretizing the 3D space. To address this limitation, we present an anchor-free parametric lane representation, which defines traffic lines as continuous curves in 3D space. Choosing splines as our representation, we show their superiority over polynomials of different degrees that were proposed in previous 2D lane detection approaches. Our continuous representation allows us to model even complex lane shapes at any position in the 3D space, while implicitly enforcing smoothness constraints. Our model is validated on a synthetic 3D lane dataset including a variety of scenes in terms of complexity of road shape and illumination. We outperform the state-of-the-art in nearly all geometric performance metrics and achieve a great leap in the detection rate. In contrast to discrete representations, our parametric model requires no post-processing achieving highest processing speed. Additionally, we provide a thorough analysis over different parametric representations for 3D lane detection. The code and trained models are available on our project website https://3d-splinenet.github.io/.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129274363","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: 1

RSF: Optimizing Rigid Scene Flow From 3D Point Clouds Without Labels RSF:从没有标签的3D点云优化刚性场景流

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00133

David Deng, A. Zakhor

引用次数: 5

ElliPose: Stereoscopic 3D Human Pose Estimation by Fitting Ellipsoids 椭圆:通过拟合椭球体来估计立体三维人体姿态

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00289

C. Grund, Julian Tanke

{"title":"ElliPose: Stereoscopic 3D Human Pose Estimation by Fitting Ellipsoids","authors":"C. Grund, Julian Tanke","doi":"10.1109/WACV56688.2023.00289","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00289","url":null,"abstract":"One of the most relevant tasks for augmented and virtual reality applications is the interaction of virtual objects with real humans which requires accurate 3D human pose predictions. Obtaining accurate 3D human poses requires careful camera calibration which is difficult for nontechnical personal or in a pop-up scenario. Recent markerless motion capture approaches require accurate camera calibration at least for the final triangulation step. Instead, we solve this problem by presenting ElliPose, Stereoscopic 3D Human Pose Estimation by Fitting Ellipsoids, where we jointly estimate the 3D human as well as the camera pose. We exploit the fact that bones do not change in length over the course of a sequence and thus their relative trajectories have to lie on the surface of a sphere which we can utilize to iteratively correct the camera and 3D pose estimation. As another use-case we demonstrate that our approach can be used as replacement for ground-truth 3D poses to train monocular 3D pose estimators. We show that our method produces competitive results even when comparing with state-of-the-art methods that use more cameras or ground-truth camera extrinsics.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116069022","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: 1

Token Pooling in Vision Transformers for Image Classification 用于图像分类的视觉变换令牌池

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00010

D. Marin, Jen-Hao Rick Chang, Anurag Ranjan, Anish K. Prabhu, Mohammad Rastegari, Oncel Tuzel

{"title":"Token Pooling in Vision Transformers for Image Classification","authors":"D. Marin, Jen-Hao Rick Chang, Anurag Ranjan, Anish K. Prabhu, Mohammad Rastegari, Oncel Tuzel","doi":"10.1109/WACV56688.2023.00010","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00010","url":null,"abstract":"Pooling is commonly used to improve the computation-accuracy trade-off of convolutional networks. By aggregating neighboring feature values on the image grid, pooling layers downsample feature maps while maintaining accuracy. In standard vision transformers, however, tokens are processed individually and do not necessarily lie on regular grids. Utilizing pooling methods designed for image grids (e.g., average pooling) thus can be sub-optimal for transformers, as shown by our experiments. In this paper, we propose Token Pooling to downsample token sets in vision transformers. We take a new perspective — instead of assuming tokens form a regular grid, we treat them as discrete (and irregular) samples of an implicit continuous signal. Given a target number of tokens, Token Pooling finds the set of tokens that best approximates the underlying continuous signal. We rigorously evaluate the proposed method on the standard transformer architecture (ViT/DeiT) and on the image classification problem using ImageNet-1k. Our experiments show that Token Pooling significantly improves the computation-accuracy trade-off without any further modifications to the architecture. Token Pooling enables DeiT-Ti to achieve the same top-1 accuracy while using 42% fewer computations.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121732093","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: 6

Aggregating Bilateral Attention for Few-Shot Instance Localization 基于多镜头实例定位的双边注意力聚合

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Pub Date : 2023-01-01 DOI: 10.1109/WACV56688.2023.00626

He-Yen Hsieh, Ding-Jie Chen, Cheng-Wei Chang, Tyng-Luh Liu

{"title":"Aggregating Bilateral Attention for Few-Shot Instance Localization","authors":"He-Yen Hsieh, Ding-Jie Chen, Cheng-Wei Chang, Tyng-Luh Liu","doi":"10.1109/WACV56688.2023.00626","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00626","url":null,"abstract":"Attention filtering under various learning scenarios has proven advantageous in enhancing the performance of many neural network architectures. The mainstream attention mechanism is established upon the non-local block, also known as an essential component of the prominent Transformer networks, to catch long-range correlations. However, such unilateral attention is often hampered by sparse and obscure responses, revealing insufficient dependencies across images/patches, and high computational cost, especially for those employing the multi-head design. To overcome these issues, we introduce a novel mechanism of aggregating bilateral attention (ABA) and validate its usefulness in tackling the task of few-shot instance localization, reflecting the underlying query-support dependency. Specifically, our method facilitates uncovering informative features via assessing: i) an embedding norm for exploring the semantically-related cues; ii) context awareness for correlating the query data and support regions. ABA is then carried out by integrating the affinity relations derived from the two measurements to serve as a lightweight but effective query-support attention mechanism with high localization recall. We evaluate ABA on two localization tasks, namely, few-shot action localization and one-shot object detection. Extensive experiments demonstrate that the proposed ABA achieves superior performances over existing methods.","PeriodicalId":270631,"journal":{"name":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113988197","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: 2