search

qyp2000 / XPSR

22 stars 1 forks source link

readme

XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution

Paper   

Yunpeng Qu1,2 | Kun Yuan2 | Kai Zhao2 | Qizhi Xie1,2 | Jinhua Hao2 | Ming Sun2 | Chao Zhou2

1Tsinghua University, 2Kuaishou Technology.

Overview framework

XPSR

Diffusion-based methods, endowed with a formidable generative prior, have received increasing attention in Image Super-Resolution (ISR) recently. However, as low-resolution (LR) images often undergo severe degradation, it is challenging for ISR models to perceive the semantic and degradation information, resulting in restoration images with incorrect content or unrealistic artifacts. To address these issues, we propose a Cross-modal Priors for Super-Resolution (XPSR) framework. Within XPSR, to acquire precise and comprehensive semantic conditions for the diffusion model, cutting-edge Multimodal Large Language Models (MLLMs) are utilized. To facilitate better fusion of cross-modal priors, a Semantic-Fusion Attention is raised. To distill semantic-preserved information instead of undesired degradations, a Degradation-Free Constraint is attached between LR and its high-resolution (HR) counterpart. Quantitative and qualitative results show that XPSR is capable of generating high-fidelity and high-realism images across synthetic and real-world datasets.

Results

xpsr

Installation

## git clone this repository
git clone https://github.com/qyp2000/XPSR.git
cd XPSR

# create an environment with python >= 3.9
conda create -n xpsr python=3.9
conda activate xpsr
pip install -r requirements.txt

Inference

Step 1: Download the pretrained models and test data

Step 2: Generate highlevel and lowlevel prompts

We use llava-v1.5-7b from huggingface to generate high-level prompts. In addition, in order to improve the model's perception of the low-level factors, we use the MLLM finetuned through q-instruct to generate low-level prompts. You can also download the two MLLMs in advance and place them into checkpoints/.

./utils_data/highlevel_prompt_test.sh
./utils_data/lowlevel_prompt_test.sh

Step 3: Run code

python test.py

You can modify the parameters in configs/xpsr_test.yaml to adapt to your specific need, such as the guidance_scale and the num_inference_steps.

Train

Step1: Download the pretrained models and training data

Step2: Generate training data

We generate training data based on the degradation pipelines of Real-ESRGAN. The generated images will be saved in trainset/.

./utils_data/make_train.sh

Based on the same approach, corresponding degraded images can be generated for the testset.

./utils_data/make_valid.sh

You can modify the args in make_valid.py to adapt to your specific need.

Step3: Generate highlevel and lowlevel prompts

Due to the significant overhead of MLLMs, we generate prompts in advance for training data so that they can be directly called during training.

./utils_data/highlevel_prompt_train.sh
./utils_data/lowlevel_prompt_train.sh

This process requires a lot of time, and we suggest that you use as many GPUs as possible to participate in the generation.

Step4: Run code

CUDA_VISIBLE_DEVICES="0,1,2,3,4,5,6,7," accelerate launch train.py

You can modify the parameters in configs/xpsr.yaml to adapt to your specific need, such as the train_batch_size and the learning_rate.

Citations

If our work is useful for your research, please consider citing:

@article{qu2024xpsr,
  title={XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution},
  author={Qu, Yunpeng and Yuan, Kun and Zhao, Kai and Xie, Qizhi and Hao, Jinhua and Sun, Ming and Zhou, Chao},
  journal={arXiv preprint arXiv:2403.05049},
  year={2024}
}

Contact

The reorganization of the codes are rushed, and there may be many problems. Please feel free to contact: qyp21@mails.tsinghua.edu.cn. I am very pleased to communicate with you and will maintain this repository during my free time.

Acknowledgments

Some codes are brought from PASD and SeeSR. Thanks for their excellent works.