Pcsr Carn

🚀 Accelerating Image Super-Resolution Networks with Pixel-Level Classification (ECCV 2024)

This project proposes a novel method, PCSR, to optimize computational resource usage in image super - resolution by distributing resources adaptively at the pixel level.

🚀 Quick Start

This project focuses on accelerating image super - resolution networks. You can quickly start by following the installation and demo steps below.

✨ Features

• Pixel - level Resource Allocation: The PCSR method assigns each pixel to an appropriate upsampler based on its restoration difficulty, optimizing computational resource usage.
• Balanced Performance and Cost: Allows for a balance between performance and computational cost during inference without re - training.
• Advantage in Trade - offs: Demonstrates an advantage over existing patch - distributing methods in PSNR - FLOP trade - offs across different backbone models and benchmarks.

📦 Installation

Dependencies

• Python 3.7
• Pytorch 1.13
• NVIDIA GPU + CUDA
• Python packages: pip install numpy opencv - python pandas tqdm fast_pytorch_kmeans

💻 Usage Examples

Basic Usage

We provide a demo that performs 4x super - resolution on a single input LR image (supports only 4x scaling and .png format).

git clone https://huggingface.co/3587jjh/pcsr_carn

and then, specify your LR image path and output path like:

python demo.py --lr_path comic.png --output_path results

Output: flops: 66.3G (63.6 %) | max_flops: 104.1G (100 %)

For detailed demo and information, please refer to our GitHub page.

Advanced Usage

The project's core algorithm can be integrated into other image super - resolution systems for more complex scenarios. You can modify the backbone model in the PCSR model and adjust the parameters of the pixel - level classifier to adapt to different datasets and tasks.

📚 Documentation

Abstract

In recent times, the need for effective super - resolution (SR) techniques has surged, especially for large - scale images ranging 2K to 8K resolutions. For DNN - based SISR, decomposing images into overlapping patches is typically necessary due to computational constraints. In such patch - decomposing scheme, one can allocate computational resources differently based on each patch's difficulty to further improve efficiency while maintaining SR performance. However, this approach has a limitation: computational resources is uniformly allocated within a patch, leading to lower efficiency when the patch contain pixels with varying levels of restoration difficulty. To address the issue, we propose the Pixel - level Classifier for Single Image Super - Resolution (PCSR), a novel method designed to distribute computational resources adaptively at the pixel level. A PCSR model comprises a backbone, a pixel - level classifier, and a set of pixel - level upsamplers with varying capacities. The pixel - level classifier assigns each pixel to an appropriate upsampler based on its restoration difficulty, thereby optimizing computational resource usage. Our method allows for performance and computational cost balance during inference without re - training. Our experiments demonstrate PCSR's advantage over existing patch - distributing methods in PSNR - FLOP trade - offs across different backbone models and benchmarks.

📄 License

No license information provided in the original README.

📚 Citation

@inproceedings{jeong2025accelerating,
  title={Accelerating Image Super-Resolution Networks with Pixel-Level Classification},
  author={Jeong, Jinho and Kim, Jinwoo and Jo, Younghyun and Kim, Seon Joo},
  booktitle={European Conference on Computer Vision},
  pages={236--251},
  year={2025},
  organization={Springer}
}