Single Image Reflection Removal Through Cascaded Refinement

  title={Single Image Reflection Removal Through Cascaded Refinement},
  author={Chao Li and Yixiao Yang and Kun He and Stephen Lin and John E. Hopcroft},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Chao LiYixiao Yang J. Hopcroft
  • Published 15 November 2019
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We address the problem of removing undesirable reflections from a single image captured through a glass surface, which is an ill-posed, challenging but practically important problem for photo enhancement. Inspired by iterative structure reduction for hidden community detection in social networks, we propose an Iterative Boost Convolutional LSTM Network (IBCLN) that enables cascaded prediction for reflection removal. IBCLN is a cascaded network that iteratively refines the estimates of… 

Figures and Tables from this paper

Image Synthesis with Appearance Decomposition

This thesis focuses on studying how appearance decomposition can improve image synthesis methods using two examples, and introduces a periodicity-aware single image framework to synthesize a scene of near-periodic patterns (NPP).

Location-aware Single Image Reflection Removal

A novel location-aware deep-learning-based single image reflection removal method that leverage Laplacian kernel parameters to emphasize the boundaries of strong reflections and substantially improves the quality of reflection removal results.

Robust Reflection Removal with Flash-only Cues in the Wild

A dedicated model is proposed that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate re-�ection and transmission.

Content and Gradient Model-driven Deep Network for Single Image Reflection Removal

This paper proposes a content and gradient-guided deep network (CGDNet) for single image reflection removal, which is a full-interpretable and model-driven network.

Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration

A novel model for ultra high-resolution image restoration, referred to as the Global-Local Stepwise Generative Network ( GLSGN), which employs a stepwise restoring strategy involving four restoring pathways: three local pathways and one global pathway.

Semantically supervised appearance decomposition for virtual staging from a single panorama

The appearance decomposition enables multiple applications including sun direction estimation, virtual furniture insertion, floor material replacement, and sun direction change, providing an effective tool for virtual home staging.

Multistage Curvature-Guided Network for Progressive Single Image Reflection Removal

A Multi-stage Curvature-guided De-Reflection Network (MCDRNet), which combines multiple network architectures in a unified framework to progressively reconstruct the background layer and refine the fine-grained details, and outperforms the state-of-the-art methods quantitatively and generates visually better reflection removal results.

DURRNet: Deep Unfolded Single Image Reflection Removal Network

A novel deep architecture called deep unfolded single image reflection removal network (DURRNet) is presented which makes an attempt to combine the best features from modelbased and learning-based paradigms and therefore leads to a more interpretable deep architecture.

A Model-Guided Unfolding Network for Single Image Reflection Removal

An explainable approach for SIRR named model-guided unfolding network(MoG-SIRR), which is unfolded from the proposed reflection removal model with non-local autoregressive prior and dereflection prior, which achieves superior performance for single image reflection removal.

U2-Former: A Nested U-shaped Transformer for Image Restoration

A deep and effective Transformer-based network for image restoration, termed as U-Former, which is able to employ Transformer as the core operation to perform image restoration in a deep encoding and decoding space and leverages the nested U-shaped structure to facilitate the interactions across different layers with different scales of feature maps.



Single Image Reflection Removal Beyond Linearity

Single Image Reflection Separation with Perceptual Losses

The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information and proposes a novel exclusion loss that enforces pixel-level layer separation.

Benchmarking Single-Image Reflection Removal Algorithms

This paper presents the first captured Single-image Reflection Removal dataset ‘SIR2’ with 40 controlled and 100 wild scenes, ground truth of background and reflection, and performs quantitative and visual quality comparisons for four state-of-the-art single-image reflection removal algorithms using four error metrics.

Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements

Experimental results collectively show that the method outperforms the state-of-the-art with aligned data, and that significant improvements are possible when using additional misaligned data.

CRRN: Multi-scale Guided Concurrent Reflection Removal Network

This paper proposes the Concurrent Reflection Removal Network (CRRN), a network that integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes.

A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing

A deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering by estimating edges and reconstructing images using only cascaded convolutional layers arranged such that no handcrafted or application-specific image-processing components are required.

Depth of field guided reflection removal

A multi-scale DoF computing strategy to classify edge pixels more efficiently is introduced and, based on the results of edge classification, the background and reflection layers can be separated.

Image quality assessment: from error visibility to structural similarity

A structural similarity index is developed and its promise is demonstrated through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000.

Hidden Community Detection in Social Networks

Revealing Multiple Layers of Hidden Community Structure in Networks

Through application of HICODE, it is demonstrated that a wide variety of real networks from different domains contain many communities that, though meaningful, are not detected by any of the popular community detection algorithms that are considered.