Learning to See Through Obstructions with Layered Decomposition
arXiv:2008.04902
Abstract
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions, or adherent raindrops, from a short sequence of images captured by a moving camera. Our method leverages motion differences between the background and 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. This learning-based layer reconstruction module facilitates accommodating potential errors in the flow estimation and brittle assumptions, such as brightness consistency. We show that the proposed approach learned from synthetically generated data performs well to real images. Experimental results on numerous challenging scenarios of reflection and fence removal demonstrate the effectiveness of the proposed method.
arXiv commentProject page: https://alex04072000.github.io/SOLD/ Code: https://github.com/alex04072000/SOLD Extension of the CVPR 2020 paper: arXiv:2004.01180
References in corpus (6)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Prototypical Networks for Few-shot Learning
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Few-Shot Learning with Graph Neural Networks
- Fast Context Adaptation via Meta-Learning
- Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation