# Seeing through Unclear Glass: Occlusion Removal with One Shot

arXiv: https://arxiv.org/abs/2509.01033 · HTML: https://mlsanity.com/paper/2509.01033/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision](https://mlsanity.com/paper/1803.11097/) (2018)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [Self-Supervised Scene De-occlusion](https://mlsanity.com/paper/2004.02788/) (2020)
- [Self-Supervised Generalisation with Meta Auxiliary Learning](https://mlsanity.com/paper/1901.08933/) (2019)
- [Image Inpainting via Conditional Texture and Structure Dual Generation](https://mlsanity.com/paper/2108.09760/) (2021)
- [Deep Optics for Monocular Depth Estimation and 3D Object Detection](https://mlsanity.com/paper/1904.08601/) (2019)
- [Deep Auxiliary Learning for Visual Localization and Odometry](https://mlsanity.com/paper/1803.03642/) (2018)
- [Fast Adaptation to Super-Resolution Networks via Meta-Learning](https://mlsanity.com/paper/2001.02905/) (2020)
- [Learning to See Through Obstructions](https://mlsanity.com/paper/2004.01180/) (2020)
- [Dual Attention-in-Attention Model for Joint Rain Streak and Raindrop Removal](https://mlsanity.com/paper/2103.07051/) (2021)
- [Let's See Clearly: Contaminant Artifact Removal for Moving Cameras](https://mlsanity.com/paper/2104.08852/) (2021)
- [Fast Point Cloud Geometry Compression with Context-based Residual Coding and INR-based Refinement](https://mlsanity.com/paper/2408.02966/) (2024)
- [Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance](https://mlsanity.com/paper/2305.07814/) (2023)

## Built on by (most cited first, 1 of 1)

- [Improving Robustness of Vision-Language-Action Models by Restoring Corrupted Visual Inputs](https://mlsanity.com/paper/2602.01158/) (2026)

## Abstract (arXiv)

Images taken through window glass are often degraded by contaminants adhered to the glass surfaces. Such contaminants cause occlusions that attenuate the incoming light and scatter stray light towards the camera. Most of existing deep learning methods for neutralizing the effects of contaminated glasses relied on synthetic training data. Few researchers used real degraded and clean image pairs, but they only considered removing or alleviating the effects of rain drops on glasses. This paper is concerned with the more challenging task of learning the restoration of images taken through glasses contaminated by a wide range of occluders, including muddy water, dirt and other small foreign particles found in reality. To facilitate the learning task we have gone to a great length to acquire real paired images with and without glass contaminants. More importantly, we propose an all-in-one model to neutralize contaminants of different types by utilizing the one-shot test-time adaptation mechanism. It involves a self-supervised auxiliary learning task to update the trained model for the unique occlusion type of each test image. Experimental results show that the proposed method outperforms the state-of-the-art methods quantitatively and qualitatively in cleaning realistic contaminated images, especially the unseen ones.