Despite the recent progress in enhancing the efficacy of image deblurring, the limited decoding capability constrains the upper limit of State-Of-The-Art (SOTA) methods. This paper proposes a pioneering work, Adaptive Patch Exiting Reversible Decoder (AdaRevD), to explore their insufficient decoding capability. By inheriting the weights of the well-trained encoder, we refactor a reversible decoder which scales up the single-decoder training to multi-decoder training while remaining GPU memory-friendly. Meanwhile, we show that our reversible structure gradually disentangles high-level degradation degree and low-level blur pattern (residual of the blur image and its sharp counterpart) from compact degradation representation. Besides, due to the spatially-variant motion blur kernels, different blur patches have various deblurring difficulties. We further introduce a classifier to learn the degradation degree of image patches, enabling them to exit at different sub-decoders for speedup. Experiments show that our AdaRevD pushes the limit of image deblurring, e.g., achieving 34.60 dB in PSNR on GoPro dataset.

翻译：尽管近期在提升图像去模糊效能方面取得了进展，但有限的解码能力制约了当前最优方法的性能上限。本文提出了一项开创性工作——自适应补丁退出可逆解码器，以探究现有方法解码能力的不足。通过继承训练完备的编码器权重，我们重构了一个可逆解码器，在保持GPU内存友好的同时，将单解码器训练扩展至多解码器训练。同时，我们证明了该可逆结构能够从紧凑的退化表示中逐步解耦高层退化程度与低层模糊模式。此外，由于空间变化的运动模糊核，不同模糊补丁的去模糊难度存在差异。我们进一步引入分类器来学习图像补丁的退化程度，使其能在不同子解码器处提前退出以实现加速。实验表明，AdaRevD突破了图像去模糊的性能极限，例如在GoPro数据集上实现了34.60 dB的峰值信噪比。