From Shadow Generation to Shadow Removal

Liu, Zhihao; Yin, Hui; Wu, Xinyi; Wu, Zhenyao; Mi, Yang; Wang, Song

doi:10.1109/cvpr46437.2021.00489

Cited by 73 publications

(74 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cun et al [35] handled the issues of color inconsistency and artifacts at the boundaries of the shadow removed area using Dual Hierarchically Aggregation Network (DHAN) and Shadow Matting Generative Adversarial Network (SMGAN). Weakly-supervised method G2R-ShadowNet [36] designed three sub-networks dedicated for shadow generation, shadow removal and image refinement. Fu et al [37] modelled the shadow removal problem from a different perspective that is auto-exposure fusion.…”

Section: B Deep Learning Based Approachesmentioning

confidence: 99%

“…To train I C , we crop randomly masked non-shadow areas from S as well as other samples in the dataset similar to [36]. Additionally, I C is trained by augmented samples where each shadow region S s is converted to 3 different samples by varying the illumination levels.…”

Section: Illumination Critic (I C )mentioning

confidence: 99%

“…Figure 6 shows qualitative results of the proposed model trained in weakly-supervised format on total three challenging samples from ISTD [26] dataset. We also visually compare with two existing and most recently published weaklysupervised shadow removal methods by Le et al [32] and G2R-ShadowNet [36] respectively. It is clearly observed that UnShadowNet performs accurately to remove shadow in complex background.…”

Section: E Qualitative Studymentioning

confidence: 99%

See 2 more Smart Citations

UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal

Dasgupta¹,

Das²,

Das³

et al. 2022

Preprint

View full text Add to dashboard Cite

Shadows are frequently encountered natural phenomena that significantly hinder the performance of computer vision perception systems in practical settings, e.g., autonomous driving. A solution to this would be to eliminate shadow regions from the images before the processing of the perception system. Yet, training such a solution requires pairs of aligned shadowed and non-shadowed images which are difficult to obtain. We introduce a novel weakly supervised shadow removal framework UnShadowNet trained using contrastive learning. It comprises of a DeShadower network responsible for removal of the extracted shadow under the guidance of an Illumination network which is trained adversarially by the illumination critic and a Refinement network to further remove artifacts. We show that UnShadowNet can also be easily extended to a fully-supervised setup to exploit the ground-truth when available. UnShadowNet outperforms existing state-of-the-art approaches on three publicly available shadow datasets (ISTD, adjusted ISTD, SRD) in both the weakly and fully supervised setups.

show abstract

Section: B Deep Learning Based Approachesmentioning

confidence: 99%

Section: Illumination Critic (I C )mentioning

confidence: 99%

Section: E Qualitative Studymentioning

confidence: 99%

See 1 more Smart Citation

UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal

Dasgupta¹,

Das²,

Das³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The same principle applies to shadow conditions as well, where the original image element is intact with a little low brightness in certain regions [195]. Such image processing uses similar computer vision techniques as in previous paragraphs and can also take the road of first generating shadows then removing them [202]. The Retinex algorithm can also be used for image enhancement in low-light conditions [203].…”

Section: Light Relatedmentioning

confidence: 99%

Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey

Zhang¹,

Carballo²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Automated Driving Systems (ADS) open up a new domain for the automotive industry and offer new possibilities for future transportation with higher efficiency and comfortable experiences. However, autonomous driving under adverse weather conditions has been the problem that keeps autonomous vehicles (AVs) from going to level 4 or higher autonomy for a long time. This paper assesses the influences and challenges that weather brings to ADS sensors in an analytic and statistical way, and surveys the solutions against inclement weather conditions. Stateof-the-art techniques on perception enhancement with regard to each kind of weather are thoroughly reported. External auxiliary solutions like V2X technology, weather conditions coverage in currently available datasets, simulators, and experimental facilities with weather chambers are distinctly sorted out. By pointing out all kinds of major weather problems the autonomous driving field is currently facing, and reviewing both hardware and computer science solutions in recent years, this survey contributes a holistic overview on the obstacles and directions of ADS development in terms of adverse weather driving conditions.

show abstract

“…These two works aim at augmenting reality of virtual object. Liu et al [35] proposed G2R-ShadowNet to generate shadow/shadow-free pairs from shadow images and shadow masks. They first cut out the original shadow region and then generate new shadows with a randomly selected shadow mask.…”

Section: Shadow Generationmentioning

confidence: 99%

Data augmentation and shadow image classification for shadow detection

Wen

Huang

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Shadow detection is an important branch of computer vision. Recently, convolutional neural network (CNN)‐based methods for shadow detection have achieved better performance than methods based on manually designed features. However, CNNs are extremely hungry for data and the training of CNN‐based shadow detector requires time‐consuming and expensive pixel‐level annotations. To alleviate this problem in shadow detection, a method of data augmentation based on generative adversarial network (GAN), named ShadowGAN, has been proposed. Given a shadow mask and a shadow‐free image, our ShadowGAN can generate shadow images with labels. To guide the training of ShadowGAN and get more realistic shadow images, scriptL1${{\cal L}_1}$ loss is further implemented to impose a restriction between real shadow images and generated shadow images. The effectiveness of ShadowGAN is demonstrated by training existing shadow detectors on enlarged dataset. In addition, to better make use of shadow‐free images in shadow detection, shadow image classification task is added for the shadow detectors. Experiments show that this task can guide the feature extraction network to learn more robust shadow features. At last, these two methods are combined and a better performance of shadow detection is achieved.

show abstract

From Shadow Generation to Shadow Removal

Cited by 73 publications

References 33 publications

UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal

UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal

Perception and Sensing for Autonomous Vehicles Under Adverse Weather Conditions: A Survey

Data augmentation and shadow image classification for shadow detection

Contact Info

Product

Resources

About