检索结果-内蒙古大学图书馆

conference on computer vision and pattern recognition (CVPR)

作者： Meng Wang Yu-Shen Liu Yue Gao Kanle Shi Yi Fang Zhizhong Han School of Software BNRist Tsinghua University Beijing China Kuaishou Technology Beijing China Center for Artificial Intelligence and Robotics New York University Abu Dhabi Abu Dhabi UAE Department of Computer Science Wayne State University Detroit USA

Deep Implicit Function (DIF) has gained much popularity as an efficient 3D shape representation. To capture geometry details, current mainstream methods divide 3D shapes into local regions and then learn each one with a local latent code via a decoder. Such local methods can capture more local details due to less diversity among local regions than global shapes. Although the diversity of local regions has been decreased compared to global approaches, the diversity in different local regions still poses a challenge in learning an implicit function when treating all regions equally using only a single decoder. What is worse, these local regions often exhibit imbalanced distributions, where certain regions have significantly fewer observations. This leads that fine geometry details could not be preserved well. To solve this problem, we propose a novel Local pattern-specific Implicit Function, named LP-DIF, to represent a shape with clusters of local regions and multiple decoders, where each decoder only focuses on one cluster of local regions which share a certain pattern. Specifically, we first extract local codes for all regions, and then cluster them into multiple groups in the latent space, where similar regions sharing a common pattern fall into one group. After that, we train multiple decoders for mining local patterns of different groups, which simplifies the learning of fine geometric details by reducing the diversity of local regions seen by each decoder. To further alleviate the data-imbalance problem, we introduce a region re-weighting module to each pattern-specific decoder using a kernel density estimator, which dynamically re-weights the regions during learning. Our LP-DIF can restore more geometry details, and thus improve the quality of 3D reconstruction. Experiments demonstrate that our method can achieve the state-of-the-art performance over previous methods. Code is available at https://***/gtyxyz/lpdif.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Report

NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Repo...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Codruta O. Ancuti Cosmin Ancuti Florin-Alexandru Vasluianu Radu Timofte Yidi Liu Xingbo Wang Yurui Zhu Gege Shi Xin Lu Xueyang Fu Zheng-Jun Zha Wei Dong Han Zhou Ruiyi Wang Xiaohong Liu Guangtao Zhai Jun Chen Wei Song Yichang Gao Jiahao Xiong Hualiang Lin Xianger Li Dong Li Mohab Kishawy Ruibin Li Seyed Amirreza Mousavi Rana Rauf Yangyi Liu Huan Liu MingSheng Tu Kele Xu JiaWen Chen Qisheng Xu Tao Sun Jin Guo Ben Shao Tianli Liu Mohao Wu Xingzhuo Yan Minghan Fu Lehan Yang Xin Lin Lu Qi Jincen Song Xiaoqian Hu Linwei Tao Hongming Chen Xiang Chen Chuanlong Xie Zhao Zhang Junhu Wang Yanyan Wei Suiyi Zhao Shengeng Tang Sampada Malagi Amogh Joshi Nikhil Akalwadi Chaitra Desai Ramesh Ashok Tabib Uma Mudenagudi Wenjing Jiang Jagadeesh Kalyanshetti Vijayalaxmi Ashok Aralikatti Yashaswini P Nitish Upasi Dikshit Hegde Ujwala Patil Sujata C

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This study examines the results of the NTIRE 2024 Challenge on Dense and Non-Homogeneous Dehazing. Innovative methods were introduced and tested using a new image dataset named DNH-HAZE. The DNH-HAZE dataset comprises 50 pairs of authentic outdoor images showcasing dense and non-homogeneous haze alongside corresponding haze-free images of identical scenes. The haze was simulated using a professional setup designed to mirror real-world hazy conditions. The competition attracted 374 participants, with 16 teams presenting solutions for the final evaluation phase. The proposed solutions showed the leading edge of image dehazing technology.

关键词： computer vision Correlation Accuracy Image edge detection conferences computer architecture Network architecture

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results

NTIRE 2024 Challenge on Short-form UGC Video Quality Assessm...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Xin Li Kun Yuan Yajing Pei Yiting Lu Ming Sun Chao Zhou Zhibo Chen Radu Timofte Wei Sun Haoning Wu Zicheng Zhang Jun Jia Zhichao Zhang Linhan Cao Qiubo Chen Xiongkuo Min Weisi Lin Guangtao Zhai JianHui Sun Tianyi Wang Lei Li Han Kong Wenxuan Wang Bing Li Cheng Luo Haiqiang Wang Xiangguang Chen Wenhui Meng Xiang Pan Huiying Shi Han Zhu Xiaozhong Xu Lei Sun Zhenzhong Chen Shan Liu Fangyuan Kong Haotian Fan Yifang Xu Haoran Xu Mengduo Yang Jie Zhou Jiaze Li Shijie Wen Mai Xu Da Li Shunyu Yao Jiazhi Du Wangmeng Zuo Zhibo Li Shuai He Anlong Ming Huiyuan Fu Huadong Ma Yong Wu Fie Xue Guozhi Zhao Lina Du Jie Guo Yu Zhang Huimin Zheng Junhao Chen Yue Liu Dulan Zhou Kele Xu Qisheng Xu Tao Sun Zhixiang Ding Yuhang Hu

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This paper reviews the NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i.e., Kuaishou/Kwai Platform. The KVQ database is divided into three parts, including 2926 videos for training, 420 videos for validation, and 854 videos for testing. The purpose is to build new benchmarks and advance the development of S-UGC VQA. The competition had 200 participants and 13 teams submitted valid solutions for the final testing phase. The proposed solutions achieved state-of-the-art performances for S-UGC VQA. The project can be found at https://***/lixinustc/KVQ-Challenge-CVPR-NTIRE2024.

关键词： Training computer vision Reviews Databases conferences Benchmark testing Quality assessment

来源：评论

学校读者我要写书评

暂无评论

Hippocampus substructure segmentation using morphological vision transformer learning

引用

PHYSICS IN MEDICINE AND BIOLOGY 2023年第23期68卷 235013-235013页

作者： Lei, Yang Ding, Yifu Qiu, Richard L. J. Wang, Tonghe Roper, Justin Fu, Yabo Shu, Hui-Kuo Mao, Hui Yang, Xiaofeng Emory Univ Dept Radiat Oncol Atlanta GA 30308 USA Emory Univ Winship Canc Inst Atlanta GA 30308 USA Mem Sloan Kettering Canc Ctr Dept Med Phys New York NY 10065 USA Dept Radiol & Imaging Sci Atlanta GA 30308 USA Winship Canc Inst Atlanta GA 30308 USA

The hippocampus plays a crucial role in memory and cognition. Because of the associated toxicity from whole brain radiotherapy, more advanced treatment planning techniques prioritize hippocampal avoidance, which depends on an accurate segmentation of the small and complexly shaped hippocampus. To achieve accurate segmentation of the anterior and posterior regions of the hippocampus from T1 weighted (T1w) MR images, we developed a novel model, Hippo-Net, which uses a cascaded model strategy. The proposed model consists of two major parts: (1) a localization model is used to detect the volume-of-interest (VOI) of hippocampus. (2) An end-to-end morphological vision transformer network (Franchi et al 2020 pattern Recognit. 102 107246, Ranem et al 2022 ieee/cvf Conf. on computer vision and pattern recognition workshops (cvprw) pp 3710-3719) is used to perform substructures segmentation within the hippocampus VOI. The substructures include the anterior and posterior regions of the hippocampus, which are defined as the hippocampus proper and parts of the subiculum. The vision transformer incorporates the dominant features extracted from MR images, which are further improved by learning-based morphological operators. The integration of these morphological operators into the vision transformer increases the accuracy and ability to separate hippocampus structure into its two distinct substructures. A total of 260 T1w MRI datasets from medical segmentation decathlon dataset were used in this study. We conducted a five-fold cross-validation on the first 200 T1w MR images and then performed a hold-out test on the remaining 60 T1w MR images with the model trained on the first 200 images. In five-fold cross-validation, the Dice similarity coefficients were 0.900 +/- 0.029 and 0.886 +/- 0.031 for the hippocampus proper and parts of the subiculum, respectively. The mean surface distances (MSDs) were 0.426 +/- 0.115 mm and 0.401 +/- 0.100 mm for the hippocampus proper and parts of th

关键词： hippocampus substructure segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Few shot font generation via transferring similarity guided global style and quantization local style

Few shot font generation via transferring similarity guided ...

引用

International conference on computer vision (ICCV)

作者： Wei Pan Anna Zhu Xinyu Zhou Brian Kenji Iwana Shilin Li School of Computer Science and Artificial Intelligence Wuhan University of Technology Human Interface Laboratory Kyushu University

Automatic few-shot font generation (AFFG), aiming at generating new fonts with only a few glyph references, reduces the labor cost of manually designing fonts. However, the traditional AFFG paradigm of style-content disentanglement cannot capture the diverse local details of different fonts. So, many component-based approaches are proposed to tackle this problem. The issue with component-based approaches is that they usually require special pre-defined glyph components, e.g., strokes and radicals, which is infeasible for AFFG of different languages. In this paper, we present a novel font generation approach by aggregating styles from character similarity-guided global features and stylized component-level representations. We calculate the similarity scores of the target character and the referenced samples by measuring the distance along the corresponding channels from the content features, and assigning them as the weights for aggregating the global style features. To better capture the local styles, a cross-attention-based style transfer module is adopted to transfer the styles of reference glyphs to the components, where the components are self-learned discrete latent codes through vector quantization without manual definition. With these designs, our AFFG method could obtain a complete set of component-level style representations, and also control the global glyph characteristics. The experimental results reflect the effectiveness and generalization of the proposed method on different linguistic scripts, and also show its superiority when compared with other state-of-the-art methods. The source code can be found at https://***/awei669/VQ-Font.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Survey

Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Marcos V. Conde Zhijun Lei Wen Li Ioannis Katsavounidis Radu Timofte Min Yan Xin Liu Qian Wang Xiaoqian Ye Zhan Du Tiansen Zhang Zhiyuan Li Hao Wei Chenyang Ge Jiangtao Lv Long Sun Jinshan Pan Jiangxin Dong Jinhui Tang Menghan Zhou Yiqiang Yan Kihwan Yoon Ganzorig Gankhuyag Jae-Hyeon Lee Ui-Jin Choi Hyeon-Cheol Moon Tae-Hyun Jeong Yoonmo Yang Jae-Gon Kim Jinwoo Jeong Sunjei Kim Xintao Qiu Yuanbo Zhou Kongxian Wu Xinwei Dai Hui Tang Wei Deng Qingquan Gao Tong Tong Long Peng Jiaming Guo Xin Di Bohao Liao Zhibo Du Peize Xia Renjing Pei Yang Wang Yang Cao Zhengjun Zha Bingnan Han Hongyuan Yu Zhuoyuan Wu Cheng Wan Yuqing Liu Haodong Yu Jizhe Li Zhijuan Huang Yuan Huang Yajun Zou Xianyu Guan Qi Jia Heng Zhang Xuanwu Yin Kunlong Zuo Dongyang Zhang Tianle Liu Huaian Chen Yi Jin CAIDAS & IFI Computer Vision Lab. University of Wurzbürg Meta

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This paper introduces a novel benchmark for efficient image upscaling as part of the AIS 2024 Real-Time Image Super-Resolution (RTSR) Challenge, which aims to up scale compressed images from 540p to native 4K resolution (4x factor) in real-time on commercial GPUs. For this, we use a diverse test set containing diverse 4K images ranging from digital art to gaming and photography. The images are compressed using the modern AVIF codec, instead of JPEG. All the proposed methods improve PSNR fidelity over Lanczos interpolation, and process images under 30ms. Out of the 160 participants, 25 teams submitted their code. This survey considers only the most novel solutions models, making it the most comprehensive benchmark on real-time SR of compressed images using modern codecs.

关键词： Surveys Photography Image coding Codecs Superresolution Transform coding Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results

NTIRE 2022 Challenge on Super-Resolution and Quality Enhance...

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Ren Yang Radu Timofte Meisong Zheng Qunliang Xing Minglang Qiao Mai Xu Lai Jiang Huaida Liu Ying Chen Youcheng Ben Xiao Zhou Chen Fu Pei Cheng Gang Yu Junyi Li Renlong Wu Zhilu Zhang Wei Shang Zhengyao Lv Yunjin Chen Mingcai Zhou Dongwei Ren Kai Zhang Wangmeng Zuo Pavel Ostyakov Vyal Dmitry Shakarim Soltanayev Chervontsev Sergey Zhussip Magauiya Xueyi Zou Youliang Yan Pablo Navarrete Michelini Yunhua Lu Diankai Zhang Shaoli Liu Si Gao Biao Wu Chengjian Zheng Xiaofeng Zhang Kaidi Lu Ning Wang Thuong Nguyen Canh Thong Bach Qing Wang Xiaopeng Sun Haoyu Ma Shijie Zhao Junlin Li Liangbin Xie Shuwei Shi Yujiu Yang Xintao Wang Jinjin Gu Chao Dong Xiaodi Shi Chunmei Nian Dong Jiang Jucai Lin Zhihuai Xie Mao Ye Dengyan Luo Liuhan Peng Shengjie Chen Xin Liu Qian Wang Boyang Liang Hang Dong Yuhao Huang Kai Chen Xingbei Guo Yujing Sun Huilei Wu Pengxu Wei Yulin Huang Junying Chen Ik Hyun Lee Sunder Ali Khowaja Jiseok Yoon ETH Z&#x00FC rich rich University of W&#x00FC rzburg

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487405

This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video. In this challenge, we proposed the LDV 2.0 dataset, which includes the LDV dataset (240 videos) and 95 additional videos. This challenge includes three tracks. Track 1 aims at enhancing the videos compressed by HEVC at a fixed QP. Track 2 and Track 3 target both the super-resolution and quality enhancement of HEVC compressed video. They require x2 and x4 super-resolution, respectively. The three tracks totally attract more than 600 registrations. In the test phase, 8 teams, 8 teams and 12 teams submitted the final results to Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution and quality enhancement of compressed video. The proposed LDV 2.0 dataset is available at https://***/RenYang-home/LDV_dataset. The homepage of this challenge (including open-sourced codes) is at https://***/RenYang-home/NTIRE22_VEnh_SR.

关键词： computer vision Target tracking Codes conferences Superresolution pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Generative Quanta Color Imaging

Generative Quanta Color Imaging

引用

conference on computer vision and pattern recognition (CVPR)

作者： Vishal Purohit Junjie Luo Yiheng Chi Qi Guo Stanley H. Chan Qiang Qiu Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette USA

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The astonishing development of single-photon cameras has created an unprecedented opportunity for scientific and industrial imaging. However, the high data throughput generated by these 1-bit sensors creates a significant bottleneck for low-power applications. In this paper, we explore the possibility of generating a color image from a single binary frame of a single-photon camera. We evidently find this problem being particularly difficult to standard colorization approaches due to the substantial degree of exposure variation. The core innovation of our paper is an exposure synthesis model framed under a neural ordinary differential equation (Neural ODE) that allows us to generate a contin-uum of exposures from a single observation. This innovation ensures consistent exposure in binary images that col-orizers take on, resulting in notably enhanced colorization. We demonstrate applications of the method in single-image and burst colorization and show superior generative performance over baselines. Project website can be found at https://***/projects/2023/generative_quanta_***

关键词： Technological innovation computer vision Color Ordinary differential equations Cameras Throughput Mathematical models

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2024 Image Shadow Removal Challenge Report

NTIRE 2024 Image Shadow Removal Challenge Report

引用

ieee computer Society conference on computer vision and pattern recognition workshops (cvprw)

作者： Florin-Alexandru Vasluianu Tim Seizinger Zhuyun Zhou Zongwei Wu Cailian Chen Radu Timofte Wei Dong Han Zhou Yuqiong Tian Jun Chen Xueyang Fu Xin Lu Yurui Zhu Xi Wang Dong Li Jie Xiao Yunpeng Zhang Zheng-Jun Zha Zhao Zhang Suiyi Zhao Bo Wang Yan Luo Yanyan Wei Zhihao Zhao Long Sun Tingting Yang Jinshan Pan Jiangxin Dong Jinhui Tang Bilel Benjdira Mohammed Nassif Anis Koubaa Ahmed Elhayek Anas M. Ali Kyotaro Tokoro Kento Kawai Kaname Yokoyama Takuya Seno Yuki Kondo Norimichi Ukita Chenghua Li Bo Yang Zhiqi Wu Gao Chen Yihan Yu Sixiang Chen Kai Zhang Tian Ye Wenbin Zou Yunlong Lin Zhaohu Xing Jinbin Bai Wenhao Chai Lei Zhu Ritik Maheshwari Rakshank Verma Rahul Tekchandani Praful Hambarde Satya Narayan Tazi Santosh Kumar Vipparthi Subrahmanyam Murala Jaeho Lee Seongwan Kim Sharif S M A Nodirkhuja Khujaev Roman Tsoy Fan Gao Weidan Yan Wenze Shao Dengyin Zhang Bin Chen Siqi Zhang Yanxin Qian Yuanbin Chen Yuanbo Zhou Tong Tong Rongfeng Wei Ruiqi Sun Yue Liu Nikhil Akalwadi Amogh Joshi Sampada Malagi Chaitra Desai Ramesh Ashok Tabib Uma Mudenagudi Ali Murtaza Uswah Khairuddin Ahmad ’Athif Mohd Faudzi Adinath Dukre Vivek Deshmukh Shruti S. Phutke Ashutosh Kulkarni Anil Gonde Arun karthik K Manasa N Shri Hari Priya Wei Hao Xingzhuo Yan Minghan Fu

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

This work reviews the results of the NTIRE 2024 Challenge on Shadow Removal. Building on the last year edition, the current challenge was organized in two tracks, with a track focused on increased fidelity reconstruction, and a separate ranking for high performing perceptual quality solutions. Track 1 (fidelity) had 214 registered participants, with 17 teams submitting in the final phase, while Track 2 (perceptual) registered 185 participants, resulting in 18 final phase submissions. Both tracks were based on data from the WSRD dataset, simulating interactions between self-shadows and cast shadows, with a large variety of represented objects, textures, and materials. Improved image alignment enabled increased fidelity reconstruction, with restored frames mostly indistinguishable from the references images for top performing solutions.

关键词： computer vision Reviews Image synthesis conferences Buildings Image restoration pattern recognition

来源：评论

学校读者我要写书评

暂无评论

TRINS: Towards Multimodal Language Models that Can Read

TRINS: Towards Multimodal Language Models that Can Read

引用

conference on computer vision and pattern recognition (CVPR)

作者： Ruiyi Zhang Yanzhe Zhang Jian Chen Yufan Zhou Jiuxiang Gu Changyou Chen Tong Sun Adobe Research Georgia Institute of Technology State University of New York at Buffalo

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Large multimodal language models have shown remarkable proficiency in understanding and editing images. However, a majority of these visually-tuned models struggle to comprehend the textual content embedded in images, primar-ily due to the limitation of training data. In this work, we introduce TRINS: a Text-Rich image 1 1 In this work, we use the phrase “text-rich images” to describe images with rich textual information, such as posters and book covers. INStruction dataset, with the objective of enhancing the reading ability of the multimodal large language model. TRINS is built upon LAION 2 2 Work done during Q3 2023. using hybrid data annotation strategies that include machine-assisted and human-assisted annotation process. It contains 39,153 text-rich images, captions, and 102,437 questions. Specifically, we show that the number of words per annotation in TRINS is significantly longer than that of related datasets, providing new challenges. Furthermore, we introduce a simple and effective architecture, called a Language-vision Reading Assistant (LaRA), which is good at understanding textual content within images. LaRA outperforms existing state-of-the-art multimodal large language models on the TRINS dataset as well as other classical benchmarks. Lastly, we conducted a comprehensive evaluation with TRINS on various text-rich image understanding and generation tasks, demonstrating its effectiveness.

关键词： Visualization computer vision Annotations Large language models Computational modeling Optical character recognition Training data

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：