Learned Dual-View Reflection Removal
- URL: http://arxiv.org/abs/2010.00702v1
- Date: Thu, 1 Oct 2020 21:59:58 GMT
- Title: Learned Dual-View Reflection Removal
- Authors: Simon Niklaus and Xuaner Cecilia Zhang and Jonathan T. Barron and Neal
Wadhwa and Rahul Garg and Feng Liu and Tianfan Xue
- Abstract summary: We propose a learning-based dereflection algorithm that uses stereo images as input.
Our evaluation on an additional real-world dataset of stereo pairs shows that our algorithm outperforms existing single-image and multi-image dereflection approaches.
- Score: 38.65673895165718
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Traditional reflection removal algorithms either use a single image as input,
which suffers from intrinsic ambiguities, or use multiple images from a moving
camera, which is inconvenient for users. We instead propose a learning-based
dereflection algorithm that uses stereo images as input. This is an effective
trade-off between the two extremes: the parallax between two views provides
cues to remove reflections, and two views are easy to capture due to the
adoption of stereo cameras in smartphones. Our model consists of a
learning-based reflection-invariant flow model for dual-view registration, and
a learned synthesis model for combining aligned image pairs. Because no dataset
for dual-view reflection removal exists, we render a synthetic dataset of
dual-views with and without reflections for use in training. Our evaluation on
an additional real-world dataset of stereo pairs shows that our algorithm
outperforms existing single-image and multi-image dereflection approaches.
Related papers
- Towards Flexible Interactive Reflection Removal with Human Guidance [75.38207315080624]
Single image reflection removal is inherently ambiguous, as both the reflection and transmission components requiring separation may follow natural image statistics.
Existing methods attempt to address the issue by using various types of low-level and physics-based cues as sources of reflection signals.
In this paper, we aim to explore a novel flexible interactive reflection removal approach that leverages various forms of sparse human guidance.
arXiv Detail & Related papers (2024-06-03T17:34:37Z) - Iterative Gradient Encoding Network with Feature Co-Occurrence Loss for
Single Image Reflection Removal [6.370905925442655]
We propose an iterative gradient encoding network for single image reflection removal.
Our method can remove reflection favorably against the existing state-of-the-art method on all imaging settings.
arXiv Detail & Related papers (2021-03-29T19:29:29Z) - Unsupervised Single-Image Reflection Separation Using Perceptual Deep
Image Priors [6.333390830515411]
We propose a novel unsupervised framework for single-image reflection separation.
We optimize the parameters of two cross-coupled deep convolutional networks on a target image to generate two exclusive background and reflection layers.
Our results show that our method significantly outperforms the closest unsupervised method in the literature for removing reflections from single images.
arXiv Detail & Related papers (2020-09-01T21:08:30Z) - Unsupervised Landmark Learning from Unpaired Data [117.81440795184587]
Recent attempts for unsupervised landmark learning leverage synthesized image pairs that are similar in appearance but different in poses.
We propose a cross-image cycle consistency framework which applies the swapping-reconstruction strategy twice to obtain the final supervision.
Our proposed framework is shown to outperform strong baselines by a large margin.
arXiv Detail & Related papers (2020-06-29T13:57:20Z) - Polarized Reflection Removal with Perfect Alignment in the Wild [66.48211204364142]
We present a novel formulation to removing reflection from polarized images in the wild.
We first identify the misalignment issues of existing reflection removal datasets.
We build a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images.
arXiv Detail & Related papers (2020-03-28T13:29:31Z) - Self-Supervised Linear Motion Deblurring [112.75317069916579]
Deep convolutional neural networks are state-of-the-art for image deblurring.
We present a differentiable reblur model for self-supervised motion deblurring.
Our experiments demonstrate that self-supervised single image deblurring is really feasible.
arXiv Detail & Related papers (2020-02-10T20:15:21Z) - Single image reflection removal via learning with multi-image
constraints [50.54095311597466]
We propose a novel learning-based solution that combines the advantages of the aforementioned approaches and overcomes their drawbacks.
Our algorithm works by learning a deep neural network to optimize the target with joint constraints enhanced among multiple input images.
Our algorithm runs in real-time and state-of-the-art reflection removal performance on real images.
arXiv Detail & Related papers (2019-12-08T06:10:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.