Summary: My Paper Reading List About IQA/VQA, Camera Tampering/Blur/Soiling Detection

List of Learning Based IQA/VQA, Camera Tampering/Blur/Soiling Detection Papers

Sik-Ho Tsang
2 min readMay 10, 2022
Image/Video Quality Can Be Degraded by Many Factors (Image from IQA-Experts-300)
  • I moved the IQA/VQA, Camera Tampering/Blur/Soiling Detection paper reading list from Summary: My Paper Reading Lists, Tutorials & Sharings to here, so that I can shorten the list for different topics.
  • Though I’ve not updated for so long yet, I know that there are many state-of-the-art approaches appeared in these few years… (Indeed, IQA/VQA is a hot topic, I may read them later…)
  • Yet, I hope this summary list can provide a beginner guide or starting point for researchers to start with their research. :)

1. Objectives

1.1. Image/Video Quality Assessment (IQA/VQA)

  • To evaluate how good/bad quality the image/video is, we would like to use some intelligent approaches, i.e. IQA/VQA.
  • With the score given by IQA/VQA algorithm, we can know the image/video quality without having the raw image/video reference (only for NR approach), which is very useful in many areas, e.g.: codec tuning, transmission network quality.

1.2. Blur Classification/Detection, Soiling/Camera-Tampering Detection

  • Also, imaging sensors capture the scene as an image. However, there are numerous factors that make the difference between the actual scene and the captured image. For example: blur, tampering, raining, snowing, soiling.

2. Image/Video Quality Assessment (IQA/VQA)

2.1. Image Quality Assessment (IQA)

FR: 2017 [DeepSim] 2018 [DeepIQA]
NR
: 2014 [IQA-CNN] 2015 [IQA-CNN++] 2016 [DeepCNN] 2017 [DeepBIQ] 2018 [DeepIQA] [MEON] 2020 [DB-CNN] 2021 [Learned Resizer]

2.2. Video Quality Assessment (VQA)

FR: 2019 [DeepVQUE]
NR: 2016 [SACONVA] 2019 [3D-CNN+LSTM] [F-RNN]

4. Other Camera-Tamper-Related

4.1. Camera Tampering Detection (CTD)

2016 [Dong’s ICDSP’16] 2019 [VFI-ConvLSTM] [UHCTD] [Mantini’s VISAPP’19]

4.2. Soiling Detection / Desoiling

2019 [Desoiling Dataset] [SoildNet] [SoilingNet] 2020 [ToiledSoilingNet] 2021 [DirtyGAN] [Pseudo-Label Ensemble]

--

--

Sik-Ho Tsang

PhD, Researcher. I share what I learn. :) Linktree: https://linktr.ee/shtsang for Twitter, LinkedIn, etc.