# CIC: Circular Image Compression

arXiv: https://arxiv.org/abs/2407.15870 · HTML: https://mlsanity.com/paper/2407.15870/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 21 of 21)

- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Lossy Image Compression with Conditional Diffusion Models](https://mlsanity.com/paper/2209.06950/) (2022)
- [Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging](https://mlsanity.com/paper/2203.17061/) (2022)
- [Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules](https://mlsanity.com/paper/2107.06463/) (2021)
- [Lossy Image Compression with Quantized Hierarchical VAEs](https://mlsanity.com/paper/2208.13056/) (2022)
- [QARV: Quantization-Aware ResNet VAE for Lossy Image Compression](https://mlsanity.com/paper/2302.08899/) (2023)
- [Towards End-to-End Image Compression and Analysis with Transformers](https://mlsanity.com/paper/2112.09300/) (2021)
- [Neural Image Compression with Text-guided Encoding for both Pixel-level and Perceptual Fidelity](https://mlsanity.com/paper/2403.02944/) (2024)
- [Deep Lossy Plus Residual Coding for Lossless and Near-lossless Image Compression](https://mlsanity.com/paper/2209.04847/) (2022)
- [Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation](https://mlsanity.com/paper/2406.00758/) (2024)
- [Learning-Driven Lossy Image Compression; A Comprehensive Survey](https://mlsanity.com/paper/2201.09240/) (2022)
- [Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks](https://mlsanity.com/paper/2009.14754/) (2020)
- [Rate-Distortion Optimized Post-Training Quantization for Learned Image Compression](https://mlsanity.com/paper/2211.02854/) (2022)
- [Exploring Resolution Fields for Scalable Image Compression with Uncertainty Guidance](https://mlsanity.com/paper/2306.08941/) (2023)
- [MOODv2: Masked Image Modeling for Out-of-Distribution Detection](https://mlsanity.com/paper/2401.02611/) (2024)
- [Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework](https://mlsanity.com/paper/2210.05436/) (2022)
- [Sensitivity Decouple Learning for Image Compression Artifacts Reduction](https://mlsanity.com/paper/2405.09291/) (2024)
- [CSwin2SR: Circular Swin2SR for Compressed Image Super-Resolution](https://mlsanity.com/paper/2301.08749/) (2023)
- [End-to-End Learned Block-Based Image Compression with Block-Level Masked Convolutions and Asymptotic Closed Loop Training](https://mlsanity.com/paper/2203.11686/) (2022)
- [CMISR: Circular Medical Image Super-Resolution](https://mlsanity.com/paper/2308.08567/) (2023)
- [ICRICS: Iterative Compensation Recovery for Image Compressive Sensing](https://mlsanity.com/paper/2207.09594/) (2022)

## Abstract (arXiv)

Learned image compression (LIC) is currently the cutting-edge method. However, the inherent difference between testing and training images of LIC results in performance degradation to some extent. Especially for out-of-sample, out-of-distribution, or out-of-domain testing images, the performance of LIC degrades significantly. Classical LIC is a serial image compression (SIC) approach that utilizes an open-loop architecture with serial encoding and decoding units. Nevertheless, according to the principles of automatic control systems, a closed-loop architecture holds the potential to improve the dynamic and static performance of LIC. Therefore, a circular image compression (CIC) approach with closed-loop encoding and decoding elements is proposed to minimize the gap between testing and training images and upgrade the capability of LIC. The proposed CIC establishes a nonlinear loop equation and proves that steady-state error between reconstructed and original images is close to zero by Taylor series expansion. The proposed CIC method possesses the property of Post-Training and Plug-and-Play which can be built on any existing advanced SIC methods. Experimental results including rate-distortion curves on five public image compression datasets demonstrate that the proposed CIC outperforms eight competing state-of-the-art open-source SIC algorithms in reconstruction capacity. Experimental results further show that the proposed method is suitable for out-of-sample testing images with dark backgrounds, sharp edges, high contrast, grid shapes, or complex patterns.