ConStyle v2: A Strong Prompter for All-in-One Image Restoration
Dongqi Fan, Junhao Zhang, Liang Chang

TL;DR
ConStyle v2 is a versatile, plug-and-play prompter that significantly enhances various U-Net based image restoration models to handle multiple degradations effectively without fine-tuning.
Contribution
The paper introduces ConStyle v2, a strong, easy-to-train prompter that improves all-in-one image restoration capabilities across different model architectures.
Findings
ConStyle v2 improves performance on multiple degradation types.
It enhances various architectures like Restormer, NAFNet, and MAXIM-1S.
Training requires less than two GPU days without fine-tuning.
Abstract
This paper introduces ConStyle v2, a strong plug-and-play prompter designed to output clean visual prompts and assist U-Net Image Restoration models in handling multiple degradations. The joint training process of IRConStyle, an Image Restoration framework consisting of ConStyle and a general restoration network, is divided into two stages: first, pre-training ConStyle alone, and then freezing its weights to guide the training of the general restoration network. Three improvements are proposed in the pre-training stage to train ConStyle: unsupervised pre-training, adding a pretext task (i.e. classification), and adopting knowledge distillation. Without bells and whistles, we can get ConStyle v2, a strong prompter for all-in-one Image Restoration, in less than two GPU days and doesn't require any fine-tuning. Extensive experiments on Restormer (transformer-based), NAFNet (CNN-based),…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image Processing Techniques · Image Processing Techniques and Applications
Methods*Communicated@Fast*How Do I Communicate to Expedia? · Concatenated Skip Connection · Convolution · Nonlinear Activation Free Network · Max Pooling · U-Net
