- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes InterIR, a deep unfolding network based on an improved second-order semi-smooth Newton optimization. It reformulates multi-degradation image restoration as an interpretable iterative optimization process. It designs an explainable convolution module for input-adaptive parameter adjustment. The method addresses the poor interpretability of existing image restoration models. InterIR achieves SOTA performance on composite degradation datasets and maintains strong performance on various single-degradation tasks.
Critical strengths
InterIR reformulates the image restoration task as an improved second-order semi-smooth Newton optimization problem. It introduces an explainable convolution module design. This design makes the modules an interpretable architecture rather than a black-box network that consists of stacked convolutions.
Critical weaknesses
-
The paper claims strong physical interpretability based on the correspondence between network steps and semi-smooth Newton iterations. This claim remains at the mathematical level and lacks empirical evidence.
- The learned degradation matrices A and B should be analyzed to verify that they correspond to real physical degradations.
- The binary masks from EPBlock should be visualized to confirm that they localize degradation regions, beyond the t-SNE clustering evidence.
- The intermediate iterations should also be analyzed to show that each module follows the intended optimization behavior. This analysis would support the claimed physical interpretability.
-
The ablation study consists of module addition and removal experiments. It does not ablate the number of IPBlock unfolding layers , a key hyperparameter. Deep unfolding network performance depends on the number of unfolded iterations. It is unclear whether the gains come from module design or from more iteration blocks. The threshold in EPBlock is a learnable parameter. The paper provides no ablation on and does not quantify the benefit of the dynamic mask mechanism.
Questions for authors
-
In the explainable convolution, a binary mask is generated by a learnable threshold . However, the hard threshold is non-differentiable. How is optimized during training ? Is shared globally or learned per layer or per channel ? Are the results sensitive to the initialization and value of ?
-
The paper states that IPBlock follows the ISN algorithm to maintain physical interpretability. However, in Eq. 10, and are not explicitly solved as in Eq. 7. They are instead learned by additional networks. How can the authors ensure that these modules still correspond to ISN iterations rather than a generic black box ? Can the authors provide a convergence analysis or a comparison with an explicit ISN solver ?
Thank you for adding the CDD-11 results and clarifying how the EPConv threshold is trained. The new comparisons are helpful, though some recent related work is still missing from the discussion. My main concern remains the physical interpretation of the unfolded stages. I understand that the reconstruction residual need not decrease at every step, but seeing how it behaves across the 16 stages would help assess whether the learned updates improve consistency with the observed image. Also, as Eq. (15) is written, the spatial softmax for a 1x1 kernel always returns one, so the 1x1 EPConv layers in Fig. 2 appear to use the same kernel for every input. I am keeping my rating at 2.