相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Kaihao Zhang et al.
Summary: Video deraining is an important task in computer vision. In this paper, we propose a new end-to-end video deraining framework called ESTINet, which utilizes deep residual networks and convolutional long short-term memory to enhance the quality and speed of video deraining.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jie Xiao et al.
Summary: Existing deep learning approaches for image de-raining face limitations due to convolutional architectures. This paper proposes an efficient transformer-based architecture that incorporates general priors of visual tasks and design complementary window-based transformer and spatial transformer to overcome these limitations and achieve better de-raining performance.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Yuyang Ding et al.
Summary: Rain can seriously affect the performance of outdoor computer vision systems, but it is difficult to remove rain using existing methods on single images. This study proposes using a light field image (LFI) to estimate depth maps and detect rain streaks, and introduces a novel GAN architecture to remove rain streaks from the LFI. Experimental results show the effectiveness of the proposed method.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Namhyun Ahn et al.
Summary: In this paper, a two-step rain removal method is proposed to adaptively remove rain streaks from images captured in various rain conditions. Additionally, a novel elementwise attentive gating block is introduced to effectively extract and remove high frequency rain streaks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Kaihao Zhang et al.
Summary: Rain often leads to degraded image quality, compromising the performance of computer vision systems. This paper proposes two rain removal networks (PRRNet and EPRRNet) that utilize stereo images and semantic information to improve image quality. Experiments demonstrate that the proposed methods achieve state-of-the-art performance on both monocular and stereo rainy datasets.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Boyun Li et al.
Summary: In this paper, the authors propose AirNet, an all-in-one image restoration network that can recover images from various unknown corruption types and levels without relying on prior knowledge. Experimental results demonstrate that the proposed method outperforms 17 image restoration baselines on different datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhendong Wang et al.
Summary: This paper introduces Uformer, an image restoration architecture based on Transformer, with a hierarchical encoder-decoder network and novel designs including locally-enhanced window Transformer block and learnable multi-scale restoration modulator. Uformer demonstrates high capability for image restoration tasks and achieves superior performance in various experiments.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Jeya Maria Jose Valanarasu et al.
Summary: Removing adverse weather conditions from images is an important problem. This study proposes a transformer-based model that can effectively remove various weather degradations and achieves significant improvements over multiple test datasets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Syed Waqas Zamir et al.
Summary: Convolutional neural networks (CNNs) perform well at learning image priors, while Transformers capture long-range pixel interactions. However, the computational complexity of Transformers makes it challenging to apply them to high-resolution image restoration tasks. This work proposes an efficient Transformer model, Restormer, which achieves state-of-the-art results on various image restoration tasks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Wending Yan et al.
Summary: Existing methods for raindrop removal focus on detecting raindrop locations and recovering backgrounds, but face challenges due to diverse raindrop sizes and appearances in both single images and videos. The proposed two-stage video-based method includes a single image module and a multiple frame module, utilizing temporal constraints and multiple frames to improve results.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Huaibo Huang et al.
Summary: This research proposes a selective wavelet attention learning method to help separate rain and background information, improving the accuracy of deraining. Introducing wavelet pooling and unpooling to the encoder-decoder network allows for learning increasingly abstract representations while preserving background details. Additionally, latent alignment learning is introduced to supervise background features and augment training data for further improving deraining results.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Boyun Li et al.
Summary: This paper proposes an unsupervised and untrained neural network model YOLY for single image dehazing, which separates and composes the observed hazy image through layer disentanglement, bypassing the traditional training paradigm to achieve promising performance.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Siyuan Li et al.
Summary: This paper presents a study and evaluation of existing single image deraining algorithms, using a new large-scale benchmark that includes images of various rain types. The assessment reveals a gap between the performance on synthetic rainy images and the practical demand on real-world images, indicating that image deraining is still a largely open problem despite recent advances.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Xueyang Fu et al.
Summary: This paper introduces a graph convolutional networks (GCNs)-based model to address the issue of single image de-raining, utilizing two graphs to extract representations from new dimensions, integrating conventional CNNs and GCNs to explore feature representations, and introducing recurrent operations for successive de-raining processes. The method achieves state-of-the-art results on both synthetic and real-world data sets by benefiting from rich information exploration and exploitation.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Engineering, Electrical & Electronic
Wenjie Luo et al.
Summary: This paper presents a method for raindrop removal using weakly supervised learning, which only requires an image collection with image-level annotations for training and achieves comparable results with state-of-the-art strongly supervised learning methods.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Lei Zhu et al.
Summary: This study introduces a gated non-local deep residual learning framework for image deraining, which can adaptively adjust the global residual transmission amount with a soft gate to avoid issues caused by global residual learning. By incorporating a non-local guided attention module and a channel-wise gated prediction module, the performance of the deraining network is significantly improved.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Ye-Tao Wang et al.
Summary: This article proposes a deep learning framework for removing rain streaks in single images, achieving state-of-the-art performance by using a kernel-guided convolutional neural network. The framework includes learning the motion blur kernel, stretching the degradation map, and training a deraining network, which effectively removes rain streaks while preserving image details.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Huaibo Huang et al.
Summary: The proposed memory-oriented semi-supervised method addresses the challenge of directly extending existing rain removal methods to real-world scenarios by enabling the network to explore and exploit rain streak properties from both synthetic and real data. The network design includes a self-supervised memory module with prototypical patterns of rain degradations, allowing for comprehensive deraining without the need for clean labels. Additionally, a self-training mechanism is introduced to transfer deraining knowledge from supervised to unsupervised cases, leading to more appealing results on both limited labeled data and unlabeled real-world images compared to recent state-of-the-art methods.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Haoran Bai et al.
Summary: The paper introduces an effective cascaded non-local residual network that estimates high-resolution images from blurry low-resolution ones by cascading the deblurring module and super-resolution module. The network first deblurs the images to generate clear features, then uses a non-local residual network as the super-resolution module to further enhance the image quality. The network employs image gradient-based constraints for edge preservation and adopts progressive upsampling mechanism for better training.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021
(2021)
Article
Computer Science, Information Systems
Yue Que et al.
Summary: This paper proposes a robust rain removal method for single images using an attentive composite residual network, which surpasses existing methods in identifying and recovering rain-affected regions. The deep network structure designed in this study outperforms previous state-of-the-art methods in handling different types of rainy images and producing visually clean images with good detail retention.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Information Systems
Yinglong Wang et al.
Summary: This paper proposes a method that combines handling rain streaks and haze-like effects in a deep learning model, forming an end-to-end network through multi-module joint training, and the results outperform several state-of-the-art methods on multiple datasets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Yanyan Wei et al.
Summary: The paper introduces a new unsupervised framework, DerainCycleGAN, for single image rain removal and generation, which utilizes transfer learning and cyclic structures effectively. It also presents an unsupervised rain attentive detector (UARD) to enhance rain information detection, and a new synthetic method for generating rain streaks, improving the processing of real rainy images.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Minghan Li et al.
Summary: This paper proposes a novel approach for rain/snow removal from surveillance videos, taking into account the dynamic statistics of rain/snow and background scenes in video sequences. The method encodes rain/snow using an online multi-scale convolutional sparse coding model, and incorporates a transformation operator for capturing background transformations. The proposed model shows high adaptability to dynamic rain/snow and background changes, and is efficient for real-time video processing.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Xiaowei Hu et al.
Summary: Analyzing the visual effects of rain based on scene depth, a comprehensive rain imaging model was formulated considering both rain streaks and fog. Through a real-time end-to-end deep neural network, a dataset named RainCityscapes was prepared for real outdoor photos, achieving superior performance compared to other state-of-the-art methods in both visual and quantitative evaluations.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Wenhan Yang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Ruoteng Li et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenhan Yang et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Rajeev Yasarla et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Engineering, Electrical & Electronic
He Zhang et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
Chih-Yang Lin et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
Dongwei Ren et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Tianyu Wang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Xiaowei Hu et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Wei Wei et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenhan Yang et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiaying Liu et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Minghan Li et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
He Zhang et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Rui Qian et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenhan Yang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Phillip Isola et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Gao Huang et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Ross Girshick
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Yu Li et al.
2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2014)
Proceedings Paper
Computer Science, Artificial Intelligence
Yi-Lei Chen et al.
2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2013)
Article
Computer Science, Artificial Intelligence
Kaiming He et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2011)
