# Let's See Clearly: Contaminant Artifact Removal for Moving Cameras

arXiv: https://arxiv.org/abs/2104.08852 · HTML: https://mlsanity.com/paper/2104.08852/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 56 references that are in the map.
- First posted on arXiv 18 Apr 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Attentive Generative Adversarial Network for Raindrop Removal from a Single Image](https://mlsanity.com/paper/1711.10098/) (2017)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation](https://mlsanity.com/paper/1907.01361/) (2019)
- [Deep Flow-Guided Video Inpainting](https://mlsanity.com/paper/1905.02884/) (2019)
- [Single Image Reflection Separation with Perceptual Losses](https://mlsanity.com/paper/1806.05376/) (2018)
- [Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN](https://mlsanity.com/paper/1904.10247/) (2019)
- [A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing](https://mlsanity.com/paper/1708.03474/) (2017)
- [Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancements](https://mlsanity.com/paper/1904.00637/) (2019)
- [Robust Video Content Alignment and Compensation for Rain Removal in a CNN Framework](https://mlsanity.com/paper/1803.10433/) (2018)
- [Learning to See Through Obstructions](https://mlsanity.com/paper/2004.01180/) (2020)
- [FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors](https://mlsanity.com/paper/1803.07487/) (2018)
- [The Visual Centrifuge: Model-Free Layered Video Representations](https://mlsanity.com/paper/1812.01461/) (2018)
- [Automatic Flare Spot Artifact Detection and Removal in Photographs](https://mlsanity.com/paper/2103.04384/) (2021)
- [Pixel-wise Dense Detector for Image Inpainting](https://mlsanity.com/paper/2011.02293/) (2020)

## Built on by (most cited first, 9 of 9)

- [Flare7K: A Phenomenological Nighttime Flare Removal Dataset](https://mlsanity.com/paper/2210.06570/) (2022)
- [Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyond](https://mlsanity.com/paper/2306.04236/) (2023)
- [LightsOut: Diffusion-based Outpainting for Enhanced Lens Flare Removal](https://mlsanity.com/paper/2510.15868/) (2025)
- [Seeing Behind Dynamic Occlusions with Event Cameras](https://mlsanity.com/paper/2307.15829/) (2023)
- [Removing Image Artifacts From Scratched Lens Protectors](https://mlsanity.com/paper/2302.05746/) (2023)
- [DeflareMamba: Hierarchical Vision Mamba for Contextually Consistent Lens Flare Removal](https://mlsanity.com/paper/2508.02113/) (2025)
- [Seeing through Unclear Glass: Occlusion Removal with One Shot](https://mlsanity.com/paper/2509.01033/) (2025)
- [3D Scene-Camera Representation with Joint Camera Photometric Optimization](https://mlsanity.com/paper/2506.20979/) (2025)
- [Under-Canopy Terrain Reconstruction in Dense Forests Using RGB Imaging and Neural 3D Reconstruction](https://mlsanity.com/paper/2601.22861/) (2026)

## Abstract (arXiv)

Contaminants such as dust, dirt and moisture adhering to the camera lens can greatly affect the quality and clarity of the resulting image or video. In this paper, we propose a video restoration method to automatically remove these contaminants and produce a clean video. Our approach first seeks to detect attention maps that indicate the regions that need to be restored. In order to leverage the corresponding clean pixels from adjacent frames, we propose a flow completion module to hallucinate the flow of the background scene to the attention regions degraded by the contaminants. Guided by the attention maps and completed flows, we propose a recurrent technique to restore the input frame by fetching clean pixels from adjacent frames. Finally, a multi-frame processing stage is used to further process the entire video sequence in order to enforce temporal consistency. The entire network is trained on a synthetic dataset that approximates the physical lighting properties of contaminant artifacts. This new dataset and our novel framework lead to our method that is able to address different contaminants and outperforms competitive restoration approaches both qualitatively and quantitatively.