| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://alex04072000.github.io/SOLD/
x-github-request-id: 189A:3655F2:91FF76:A3ABDF:6952AC0C
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 16:27:57 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210076-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767025678.674436,VS0,VE207
vary: Accept-Encoding
x-fastly-request-id: 2d41505b284bed6e99d20f60f7a4469955f8c2aa
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Mon, 17 Jan 2022 13:52:36 GMT
access-control-allow-origin: *
etag: W/"61e574a4-2aac"
expires: Mon, 29 Dec 2025 16:37:58 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: E8AA:3655F2:91FF7C:A3ABE4:6952AC0C
accept-ranges: bytes
age: 0
date: Mon, 29 Dec 2025 16:27:58 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210076-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767025678.894984,VS0,VE220
vary: Accept-Encoding
x-fastly-request-id: 1e9d88ed89080733c41b09111c89716b168de3ef
content-length: 3338
Learning to See Through Obstructions
Learning to See Through Obstructions with Layered Decomposition
Abstract
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera.
Our method leverages the motion differences between the background and the obstructing elements to recover both layers.
Specifically, we alternate between estimating dense optical flow fields of the two layers and reconstructing each layer from the flow-warped images via a deep convolutional neural network.
The learning-based layer reconstruction allows us to accommodate potential errors in the flow estimation and brittle assumptions such as brightness consistency.
We show that training on synthetically generated data transfers well to real images.
Our results on numerous challenging scenarios of reflection and fence removal demonstrate the effectiveness of the proposed method.
Citation
Yu-Lun Liu, Wei-Sheng Lai, Ming-Hsuan Yang, Yung-Yu Chuang, and Jia-Bin Huang, "Learning to See Through Obstructions with Layered Decomposition", 2020
Bibtex
@article{Liu-TPAMI-2021,
author = {Liu, Yu-Lun and Lai, Wei-Sheng and Yang, Ming-Hsuan and Chuang, Yung-Yu and Huang, Jia-Bin},
title = {Learning to See Through Obstructions with Layered Decomposition},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2021}
}
Download
References
- • The visual centrifuge: Model-free layered video representations, CVPR, 2019.
- • Accurate and efficient video de-fencing using convolutional neural networks and temporal information, ICME, 2018.
- • A generic deep architecture for single image reflection removal and image smoothing, ICCV, 2017.
- • Robust separation of reflection from multiple images, CVPR, 2014.
- • Exploiting reflection change for automatic reflection removal, ICCV, 2013.
- • Video reflection removal through spatio-temporal optimization, ICCV, 2017.
- • A Computational Approach for Obstruction-Free Photography, SIGGRAPH, 2015.
- • A deep learning approach for single image reflection removal, ECCV, 2018.
- • Single image reflection separation with perceptual losses, CVPR, 2018.
- • Learning to See Through Obstructions, CVPR, 2020.