RainFlow: Optical Flow Under Rain Streaks and Rain Veiling Effect

Li, Ruoteng; Tan, Robby T.; Cheong, Loong-Fah; Avilés-Rivero, Angelica I.; Fan, Qingnan; Schoenlieb, Carola

doi:10.1109/iccv.2019.00740

Cited by 38 publications

(28 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6 for the uncertainty outputs from our network. We train our model on ChairThingsMix [28]. We do not retrain or fine-tune the PWC-Net on any of the data used in our experiments.…”

Section: Network Detailsmentioning

confidence: 99%

NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction

Singh¹,

Sanket²,

Parameshwara³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…6 for the uncertainty outputs from our network. We train our model on ChairThingsMix [28]. We do not retrain or fine-tune the PWC-Net on any of the data used in our experiments.…”

Section: Network Detailsmentioning

confidence: 99%

NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction

Singh¹,

Sanket²,

Parameshwara³

et al. 2021

Preprint

View full text Add to dashboard Cite

“…[12] addressed low-light enhancement problem using a dark channel prior. Motivated by these methods, we use a deveiling operator [31,34] to learn a latent mask A that enhances features from low-light conditions as follows…”

Section: Fusion Cell Architecturementioning

confidence: 99%

Network Architecture Search for Face Enhancement

Yasarla¹,

Joze²,

Patel³

2021

Preprint

View full text Add to dashboard Cite

Various factors such as ambient lighting conditions, noise, motion blur, etc. affect the quality of captured face images. Poor quality face images often reduce the performance of face analysis and recognition systems. Hence, it is important to enhance the quality of face images collected in such conditions. We present a multi-task face restoration network, called Network Architecture Search for Face Enhancement (NASFE), which can enhance poor quality face images containing a single degradation (i.e. noise or blur) or multiple degradations (noise+blur+low-light). During training NASFE uses clean face images of a person present in the degraded image to extract the identity information in terms of features for restoring the image. Furthermore, the network is guided by an identity-loss so that the identity information is maintained in the restored image. Additionally, we propose a network architecture search-based fusion network in NASFE which fuses the task-specific features that are extracted using the task-specific encoders. We introduce FFT-op and deveiling operators in the fusion network to efficiently fuse the task-specific features. Comprehensive experiments on synthetic and real images demonstrate that the proposed method outperforms many recent state-of-theart face restoration and enhancement methods in terms of quantitative and visual performance. * Work performed during internship at Microsoft Degraded image Super-FAN [2] Shen et al. [66] UMSN [83] DeblurGANv2[28] DFDNet [35] HiFaceGAN [80] NASFE (ours)

show abstract

“…Zheng et al [49] proposed a data-driven method to learn optical flow from low-light images. Li et al [29] proposed a RainFlow to handle heavy rain. Yan et al [45] proposed a semi-supervised network to deal with dense foggy scenes.…”

Section: Optical Flowmentioning

confidence: 99%

GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning

Li¹,

Luo²,

Liu³

2021

Preprint

View full text Add to dashboard Cite

Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy are broken. To address this problem, we present an unsupervised learning approach that fuses gyroscope into optical flow learning. Specifically, we first convert gyroscope readings into motion fields named gyro field. Then, we design a self-guided fusion module to fuse the background motion extracted from the gyro field with the optical flow and guide the network to focus on motion details. To the best of our knowledge, this is the first deep learningbased framework that fuses gyroscope data and image content for optical flow learning. To validate our method, we propose a new dataset that covers regular and challenging scenes. Experiments show that our method outperforms the state-of-art methods in both regular and challenging scenes.

show abstract

RainFlow: Optical Flow Under Rain Streaks and Rain Veiling Effect

Cited by 38 publications

References 42 publications

NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction

NudgeSeg: Zero-Shot Object Segmentation by Repeated Physical Interaction

Network Architecture Search for Face Enhancement

GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning

Contact Info

Product

Resources

About