Video Desnowing and Deraining Based on Matrix Decomposition

Ren, Weihong; Tian, Jinshou; Han, Zhi; Chan, Antoni B.; Tang, Yandong

doi:10.1109/cvpr.2017.303

Cited by 173 publications

(109 citation statements)

References 36 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…5, it can be seen that most competing methods have not finely removed snow from the video, and the separated snow layer by MS-CSC method improperly contains certain moving objects. Comparatively, the OTMS-CSC method has a better [16] (c) Jiang et al [18] (d) Ren et al [11] (e) Wei et al [12] (f) Liu et al [13] (g) MS-CSC (h) OTMS-CSC (a) Input (b) Garg et al [16] (c) Jiang et al [18] (d) Ren et al [11] (e) Wei et al [12] (f) Liu et al [13] (g) MS-CSC (h) OTMS-CSC performance in both snow removing and background/foreground detail preservation.…”

Section: Experiments On Videos With Synthetic Rain/snowmentioning

confidence: 98%

“…By contrast, the OTMS-CSC method, as well as MS-SCS, is capable of better removing all the rain streaks without mixing extra information into the rain layer. (e) Liu et al [13] (f) TMS-CSC (g) OTMS-CSC (a) Input (b) Garg et al [5] (c) Jiang et al [18] (d) Ren et al [11] (e) Liu et al [13] (f) TMS-CSC (g) OTMS-CSC Fig. 9 and Fig.…”

Section: Experiments On Videos With Real Rain/snowmentioning

confidence: 99%

“…We first introduce experiments executed on four videos with synthetic rain/snow, three with static backgrounds, as shown in Fig. 3 -5, and one with evidently dynamic background with (a) Input/GT (b) Garg et al [16] (c) Jiang et al [18] (d) Ren et al [11] (e) Wei et al [12] (f) Liu et al [13] (g) MS-CSC (h) OTMS-CSC (a) Input (b) GT (c) Garg et al [16] (d) Jiang et al [18] (e) Ren et al [11] (f) Wei et al [12] (g) Liu et al [13] (h) MS-CSC (i) OTMS-CSC [16] (c) Jiang et al [18] (d) Ren et al [11] (e) Wei et al [12] (f) Liu et al [13] (f) MS-CSC (g) OTMS-CSC (a) Input (b) Garg et al [5] (c) Jiang et al [18] (d) Ren et al [11] (e) Groundtruth (f) Liu et al [13] (g) TMS-CSC (h) OTMS-CSC sequences, respectively. The rain/snow with various types were synthetically generated by Photoshop on a black background.…”

Section: Experiments On Videos With Synthetic Rain/snowmentioning

confidence: 99%

“…https://www.youtube.com/watch? {v=KzEv1h-JgaY, v=kNTYEKjXqzs, v=wb3gWRcKyCI, v=HbgoKKj7TNA} (a) Input (b) Garg et al [16] (c) Jiang et al [18] (d) Ren et al [11] (e) Wei et al [12] (f) Liu et al [13] (g) MS-CSC (h) OTMS-CSC (e) Wei et al [12] (f) Liu et al [13] (g) MS-CSC (h) OTMS-CSC (a) Input (b) Garg et al [5] (c) Jiang et al [18] (d) Ren et al [11] (e) Liu et al [13] (f) TMS-CSC (g) OTMS-CSC The videos shown in Fig. 7 and Fig.…”

Section: Experiments On Videos With Real Rain/snowmentioning

confidence: 99%

“…In recent years, lowrank models [10] show a great potential for this task and always achieve state-of-the-art performance due to their better consideration of video structure prior knowledge both in foreground and background. Specifically, these methods not only use the low-rank structure for the background, but also fully facilitate the prior knowledge of the rain, such as sparsity and spatial smoothness [11], [12]. Very recently, deep learning based methods have also been proposed for this task.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Video Rain Streak Removal by Multiscale Convolutional Sparse Coding

Xie

Zhao

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

193

168

View full text Add to dashboard Cite

Video rain/snow removal from surveillance videos is an important task in the computer vision community since rain/snow existed in videos can severely degenerate the performance of many surveillance system. Various methods have been investigated extensively, but most only consider consistent rain/snow under stable background scenes. Rain/snow captured from practical surveillance camera, however, is always highly dynamic in time with the background scene transformed occasionally. To this issue, this paper proposes a novel rain/snow removal approach, which fully considers dynamic statistics of both rain/snow and background scenes taken from a video sequence. Specifically, the rain/snow is encoded as an online multi-scale convolutional sparse coding (OMS-CSC) model, which not only finely delivers the sparse scattering and multi-scale shapes of real rain/snow, but also well encodes their temporally dynamic configurations by real-time ameliorated parameters in the model. Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence. The approach so constructed can naturally better adapt to the dynamic rain/snow as well as background changes, and also suitable to deal with the streaming video attributed its online learning mode. The proposed model is formulated in a concise maximum a posterior (MAP) framework and is readily solved by the ADMM algorithm. Compared with the state-of-the-art online and offline video rain/snow removal methods, the proposed method achieves better performance on synthetic and real videos datasets both visually and quantitatively. Specifically, our method can be implemented in relatively high efficiency, showing its potential to real-time video rain/snow removal.Index Terms-multi-scale, convolutional sparse coding, rain/snow removal, online learning, alignment method.

show abstract

Section: Experiments On Videos With Synthetic Rain/snowmentioning

confidence: 98%

Section: Experiments On Videos With Real Rain/snowmentioning

confidence: 99%

Section: Experiments On Videos With Synthetic Rain/snowmentioning

confidence: 99%

Section: Experiments On Videos With Real Rain/snowmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Video Rain Streak Removal by Multiscale Convolutional Sparse Coding

Xie

Zhao

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

193

168

View full text Add to dashboard Cite

show abstract

Self-attentive Pyramid Network for Single Image De-raining

Guo

Dai

et al. 2019

Neural Information Processing

View full text Add to dashboard Cite

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Luo

Ren

Wang

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Rain is a common natural phenomenon. Taking images in the rain however often results in degraded quality of images, thus compromises the performance of many computer vision systems. Most existing de-rain algorithms use only one single input image and aim to recover a clean image. Few work has exploited stereo images. Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignore semantic information. In this paper, we present a Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information.

show abstract

Video Desnowing and Deraining Based on Matrix Decomposition

Cited by 173 publications

References 36 publications

Video Rain Streak Removal by Multiscale Convolutional Sparse Coding

Video Rain Streak Removal by Multiscale Convolutional Sparse Coding

Self-attentive Pyramid Network for Single Image De-raining

Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding

Contact Info

Product

Resources

About