Single Image Reflection Removal With Physically-Based Training Images

Kim, Soomin; Huo, Yuchi; Yoon, Sung‐Eui

doi:10.1109/cvpr42600.2020.00521

Cited by 63 publications

(53 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data include SRST data, reflection with moderate intensity or strong intensity. As we can see, these methods [11,32,30] are often the first, second, and third best-performing methods.…”

Section: Discussionmentioning

confidence: 89%

“…The methods [32,30] trained on real data achieve better performance on general real-scene data. Since Kim et al [11] synthesized physically-based data for training, they also achieve good performance on real-world data. These data include SRST data, reflection with moderate intensity or strong intensity.…”

Section: Discussionmentioning

confidence: 99%

“…The baselines for comparison in our experiment include CEILNet [5], CoRRN [30], BDN [37], Zhang et al [40], Wei et al [32], Yang et al [38], Arvanitopoulos et al [3], Li et al [17], IBCLN [15], and Kim et al [11]. All these methods take a single RGB image as input.…”

Section: Methodsmentioning

confidence: 99%

“…To obtain more realistic and diverse data, Wen et al [33] and Ma et al [20] propose to synthesize data using a deep neural network and achieve better performance and generalization. Kim et al [11] propose a physics based method to render the reflection and achieve better performance than using synthetic images.…”

Section: Single Image Reflection Removalmentioning

confidence: 99%

See 3 more Smart Citations

A Categorized Reflection Removal Dataset with Diverse Real-world Scenes

Lei¹,

Huang²,

Qi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Due to the lack of a large-scale reflection removal dataset with diverse real-world scenes, many existing reflection removal methods are trained on synthetic data plus a small amount of real-world data, which makes it difficult to evaluate the strengths or weaknesses of different reflection removal methods thoroughly. Furthermore, existing real-world benchmarks and datasets do not categorize image data based on the types and appearances of reflection (e.g., smoothness, intensity), making it hard to analyze reflection removal methods. Hence, we construct a new reflection removal dataset that is categorized, diverse, and real-world (CDR). A pipeline based on RAW data is used to capture perfectly aligned input images and transmission images. The dataset is constructed using diverse glass types under various environments to ensure diversity. By analyzing several reflection removal methods and conducting extensive experiments on our dataset, we show that state-of-the-art reflection removal methods generally perform well on blurry reflection but fail in obtaining satisfying performance on other types of real-world reflection. We believe our dataset can help develop novel methods to remove real-world reflection better. Our dataset is available at https://alexzhao-hugga.github.io/Real-World-Reflection-Removal/.

show abstract

Section: Discussionmentioning

confidence: 89%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Single Image Reflection Removalmentioning

confidence: 99%

See 2 more Smart Citations

A Categorized Reflection Removal Dataset with Diverse Real-world Scenes

Lei¹,

Huang²,

Qi³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Meanwhile, our model shows superior performance on SIR 2 benchmark. Because the codes of Ma et al [34] and Kim et al [18] have not been published yet, we compare the numerical results (which are from their published paper) on the subset of the SIR 2 (i.e.Wild Scenes). As reported in the SIR* in Table 5, our method shows consistently efective results.…”

Section: Comparison With the State-of-the-art Methodsmentioning

confidence: 99%

Semantic Guided Single Image Reflection Removal

Liu

Li²,

You

et al. 2022

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

Reflection is common when we see through a glass window, which not only is a visual disturbance but also influences the performance of computer vision algorithms. Removing the reflection from a single image, however, is highly ill-posed since the color at each pixel needs to be separated into two values belonging to the clear background and the reflection respectively. To solve this, existing methods use additional priors such as reflection layer smoothness, double reflection effect, and color consistency to distinguish the two layers. However, these low-level priors may not be consistently valid in real cases. In this paper, inspired by the fact that human beings can separate the two layers easily by recognizing the objects and understanding the scene, we propose to use the object semantic cue, which is high-level information, as the guidance to help reflection removal. Based on the data analysis, we develop a multi-task end-to-end deep learning method with a semantic guidance component, to solve reflection removal and semantic segmentation jointly. Extensive experiments on different datasets show significant performance gain when using high-level object-oriented information. We also demonstrate the application of our method to other computer vision tasks.

show abstract

Zero-Shot Learning for Reflection Removal of Single 360-Degree Image

Han

Sim

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Single Image Reflection Removal With Physically-Based Training Images

Cited by 63 publications

References 28 publications

A Categorized Reflection Removal Dataset with Diverse Real-world Scenes

A Categorized Reflection Removal Dataset with Diverse Real-world Scenes

Semantic Guided Single Image Reflection Removal

Zero-Shot Learning for Reflection Removal of Single 360-Degree Image

Contact Info

Product

Resources

About