BluRef: Unsupervised Image Deblurring with Dense-Matching References

Abstract

This paper introduces a novel unsupervised approach for image deblurring that utilizes a simple process for training data collection, thereby enhancing the applicability and effectiveness of deblurring methods. Our technique does not require meticulously paired data of blurred and corresponding sharp images; instead, it uses unpaired blurred and sharp images of similar scenes to generate pseudo-ground truth data by leveraging a dense matching model to identify correspondences between a blurry image and reference sharp images. Thanks to the simplicity of the training data collection process, our approach does not rely on existing paired training data or pre-trained networks, making it more adaptable to various scenarios and suitable for networks of different sizes, including those designed for low-resource devices. We demonstrate that this novel approach achieves state-of-the-art performance, marking a significant advancement in the field of image deblurring.

Figures (7)

• Figure 1: Comparison of three approaches to image deblurring. Supervised deblurring requires costly paired data, limiting scalability. Reblurring-based methods rely on indirect mappings and suitable intermediate domains, which can be hard to identify. In contrast, the proposed BluRef directly learns from unpaired blurry and reference images within the target domain, offering an efficient and scalable solution without requiring paired supervision or complex multi-stage pipelines.
• Figure 2: Iterative approach for generating a pseudo-sharp image and using it to train the deblurring model. In each epoch, the reference images $\{I_{\text{ref}}^n\}_{n=1}^N$ are matched with the deblurred result $I_{\text{deblur}}^{(k)}$ to produce the updated pseudo-sharp image and the corresponding confidence mask, which serve as the supervision targets for training the deblurring model.
• Figure 3: Protocol to collect sharp reference images in our experiments. For each blurry image, we collect $N$ sharp reference images as the two groups of consecutive frames from both sides, each displaced by $\Delta$ frames from the blurry image.
• Figure 4: Qualitative results of several methods on GoPro and RB2V data. This figure presents four examples, two from each dataset. For each example, a zoomed-in portion of the input image is displayed, accompanied by its ground truth counterpart and the results from BluRef and three other baselines. Additional results are included in the supplementary material.
• Figure 5: Visualization of blur and sharp images along with corresponding reference frames used for training BluRef.