Robust Reflection Removal with Reflection-free Flash-only Cues

@article{Lei2021RobustRR,
  title={Robust Reflection Removal with Reflection-free Flash-only Cues},
  author={Chenyang Lei and Qifeng Chen},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2021},
  pages={14806-14815}
}
  • Chenyang Lei, Qifeng Chen
  • Published 7 March 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. We observe that this flash-only image is visually reflection-free, and thus it can provide robust cues to infer the… Expand
A Categorized Reflection Removal Dataset with Diverse Real-world Scenes
TLDR
It is shown 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. Expand
Invertible Image Signal Processing
TLDR
An Invertible Image Signal Processing (InvISP) pipeline is designed, which not only enables rendering visually appealing sRGB images but also allows recovering nearly perfect RAW data. Expand
Neural Camera Simulators
TLDR
This work represents the first attempt to simulate a camera sensor’s behavior leveraging both the advantage of traditional raw sensor features and the power of data-driven deep learning. Expand

References

SHOWING 1-10 OF 50 REFERENCES
The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
TLDR
A new dataset of human perceptual similarity judgments is introduced and it is found that deep features outperform all previous metrics by large margins on this dataset, and suggests that perceptual similarity is an emergent property shared across deep visual representations. Expand
Siamese Dense Network for Reflection Removal with Flash and No-Flash Image Pairs
TLDR
The proposed siamese dense network (SDN) for reflection removal with flash and no-flash image pairs outperforms state-of-the-art ones in terms of visual quality and quantitative measurements and applies to color/depth image pairs and achieves both color reflection removal and depth filling. Expand
Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements
TLDR
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. Expand
Removing photography artifacts using gradient projection and flash-exposure sampling
TLDR
A novel gradient projection scheme based on a gradient coherence model that allows removal of reflections and highlights from flash images and a brightness-ratio based algorithm that allows for the falloff in the flash image brightness due to depth is presented. Expand
Invertible Image Signal Processing
TLDR
An Invertible Image Signal Processing (InvISP) pipeline is designed, which not only enables rendering visually appealing sRGB images but also allows recovering nearly perfect RAW data. Expand
CycleISP: Real Image Restoration via Improved Data Synthesis
TLDR
This paper presents a framework that models camera imaging pipeline in forward and reverse directions that allows any number of realistic image pairs for denoising both in RAW and sRGB spaces and achieves the state-of-the-art performance on real camera benchmark datasets. Expand
Fast Single Image Reflection Suppression via Convex Optimization
TLDR
A convex model to suppress the reflection from a single input image is proposed, which implies a partial differential equation with gradient thresholding, which is solved efficiently using Discrete Cosine Transform. Expand
A Software Platform for Manipulating the Camera Imaging Pipeline
TLDR
A new software platform that allows easy access to each stage of the camera imaging pipeline and modification of the parameters for individual components as well as the ability to access and manipulate the intermediate images as they pass through different stages is presented. Expand
Learning to See in the Dark
TLDR
A pipeline for processing low-light images is developed, based on end-to-end training of a fully-convolutional network that operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. Expand
Blind Video Temporal Consistency via Deep Video Prior
TLDR
This work shows that temporal consistency can be achieved by training a convolutional network on a video with the Deep Video Prior, and proposes a carefully designed iteratively reweighted training strategy to address the challenging multimodal inconsistency problem. Expand
...
1
2
3
4
5
...