Published on Wed Dec 06 2017

Separating Reflection and Transmission Images in the Wild

Patrick Wieschollek, Orazio Gallo, Jinwei Gu, Jan Kautz

State-of-the-art methods can remove reflections on synthetic data and in controlled scenarios. However, they are based on strong assumptions and do not generalize well to real-world images. We present a deep learning approach to separate the reflected and the transmitted components of the recorded images.

0
0
0
Abstract

The reflections caused by common semi-reflectors, such as glass windows, can impact the performance of computer vision algorithms. State-of-the-art methods can remove reflections on synthetic data and in controlled scenarios. However, they are based on strong assumptions and do not generalize well to real-world images. Contrary to a common misconception, real-world images are challenging even when polarization information is used. We present a deep learning approach to separate the reflected and the transmitted components of the recorded irradiance, which explicitly uses the polarization properties of light. To train it, we introduce an accurate synthetic data generation pipeline, which simulates realistic reflections, including those generated by curved and non-ideal surfaces, non-static scenes, and high-dynamic-range scenes.

Sun Dec 09 2018
Computer Vision
Deep Spectral Reflectance and Illuminant Estimation from Self-Interreflections
CNN-based approach to estimate the spectral reflectance of a surface and the spectral power distribution of the light from a single RGB image of a V-shaped surface.
0
0
0
Sun Mar 27 2016
Computer Vision
DeLight-Net: Decomposing Reflectance Maps into Specular Materials and Natural Illumination
This is a notoriously difficult problem,yet key to various re-rendering applications. We propose a Convolutional Neural Network (CNN) architecture to construct both material parameters (i.e. Phong) as well as illumination.
0
0
0
Sat Mar 28 2020
Computer Vision
Polarized Reflection Removal with Perfect Alignment in the Wild
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. Second, capitalizing on the special relationship between reflection and polarized light, we propose a polarized reflection removal model.
0
0
0
Wed Jan 31 2018
Computer Vision
Single Image Reflection Removal Using Deep Encoder-Decoder Network
Image of a scene captured through a piece of transparent and reflective material, such as glass, is often spoiled by a superimposed layer of reflection. We propose a novel deep convolutional encoder-decoder method to remove the objectionable reflection.
0
0
0
Mon Dec 07 2020
Computer Vision
NeRD: Neural Reflectance Decomposition from Image Collections
Decomposing a scene into its shape, reflectance, and illumination is a challenging but essential problem in computer vision and graphics. NeRD is a method that achieves this decomposition by introducing physically-based rendering to neurological radiance fields.
2
0
0
Fri May 14 2021
Computer Vision
Predicting Surface Reflectance Properties of Outdoor Scenes Under Unknown Natural Illumination
The paper proposes a framework to predict surface reflectance properties of outdoor scenes under unknown natural illumination. The model is based on a combination of phenomenological and physics-based scattering models.
1
0
0