IEEE Workshop/Winter Conference on Applications of Computer Vision最新文献

Combining RGB and ToF cameras for real-time 3D hand gesture interaction 结合RGB和ToF相机进行实时3D手势交互

IEEE Workshop/Winter Conference on Applications of Computer Vision Pub Date : 2011-01-05 DOI: 10.1109/WACV.2011.5711485

M. Bergh, L. Gool

引用次数: 199

Introductory message from WACV 2009 general chair 2009年WACV总主席的介绍性讲话

IEEE Workshop/Winter Conference on Applications of Computer Vision Pub Date : 2009-12-01 DOI: 10.1109/WACV.2009.5403132

B. Morse

引用次数: 0

Automated performance evaluation of range image segmentation 距离图像分割的自动性能评价

IEEE Workshop/Winter Conference on Applications of Computer Vision Pub Date : 2000-12-04 DOI: 10.1109/WACV.2000.895418

Jaesik Min, M. Powell, K. Bowyer

引用次数: 13

A methodology for evaluating range image segmentation techniques 一种评估距离图像分割技术的方法

IEEE Workshop/Winter Conference on Applications of Computer Vision Pub Date : 1994-12-05 DOI: 10.1109/ACV.1994.341320

A. Hoover, G. Jean-Baptiste, Dmitry Goldgof, K. Bowyer

引用次数: 21

WHFL: Wavelet-Domain High Frequency Loss for Sketch-to-Image Translation 基于小波域高频损失的草图到图像转换

IEEE Workshop/Winter Conference on Applications of Computer Vision Pub Date : 1900-01-01 DOI: 10.1109/WACV56688.2023.00081

Min Woo Kim, N. Cho

{"title":"WHFL: Wavelet-Domain High Frequency Loss for Sketch-to-Image Translation","authors":"Min Woo Kim, N. Cho","doi":"10.1109/WACV56688.2023.00081","DOIUrl":"https://doi.org/10.1109/WACV56688.2023.00081","url":null,"abstract":"Even a rough sketch can effectively convey the descriptions of objects, as humans can imagine the original shape from the sketch. The sketch-to-photo translation is a computer vision task that enables a machine to do this imagination, taking a binary sketch image and generating plausible RGB images corresponding to the sketch. Hence, deep neural networks for this task should learn to generate a wide range of frequencies because most parts of the input (binary sketch image) are composed of DC signals. In this paper, we propose a new loss function named Wavelet-domain High-Frequency Loss (WHFL) to overcome the limitations of previous methods that tend to have a bias toward low frequencies. The proposed method emphasizes the loss on the high frequencies by designing a new weight matrix imposing larger weights on the high bands. Unlike existing handcraft methods that control frequency weights using binary masks, we use the matrix with finely controlled elements according to frequency scales. The WHFL is designed in a multi-scale form, which lets the loss function focus more on the high frequency according to decomposition levels. We use the WHFL as a complementary loss in addition to conventional ones defined in the spatial domain. Experiments show we can improve the qualitative and quantitative results in both spatial and frequency domains. Additionally, we attempt to verify the WHFL’s high-frequency generation capability by defining a new evaluation metric named Unsigned Euclidean Distance Field Error (UEDFE).","PeriodicalId":236308,"journal":{"name":"IEEE Workshop/Winter Conference on Applications of Computer Vision","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129729680","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