- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes an all-in-one framework for restoring polarization images under diverse and composite degradations. Based on a representation study, the authors adopt the normalized Stokes representation and design a dual-branch network. In this network design, the intensity branch exploits pretrained InstructIR priors with an MoE extension, and an adaptive cross-domain module transfers these priors to a lightweight polarization branch. The authors also build PolarCDD, a composite-degradation benchmark with 11 degradation settings and report consistent gains over general AIO and polarization-specific methods.
Critical strengths
- A valuable composite-degradation benchmark. PolarCDD covers 11 single and composite degradation settings with 50K training images per setting. It also incorporates real captured data: low-light images acquired with a DoT system and a real-noise subset. This fills a clear gap, since existing polarization datasets mostly target a single degradation, and it should facilitate future research on AIO polarization restoration.
- The proposed method yields consistent improvements when built on NAFNet, Restormer, MoCE-IR, and InstructIR. It also maintains competitive memory usage and latency (Tab. 6).
Critical weaknesses
- The investigation of polarization representations is presented as a core contribution (Sec. 3.2, contribution (1)). However, the comparison in Tab. 1 is conducted only with a single NAFNet backbone, so it ignores how network architecture and capacity may affect the conclusion. The representation study is insufficient to support one of the paper’s key contributions. The authors should repeat this comparison within their own proposed architecture, and ideally with at least one more backbone. This would more convincingly establish that the normalized Stokes representation is the right choice.
- The insight and motivation behind the network design are unclear. Why MoE for the intensity branch? The authors extend the intensity branch into an MoE architecture to improve its handling of composite degradations. It is unclear why this is preferable to simply increasing network depth or the parameter count of the branch. The MoE ablation (Tabs. 10–11) compares only with and without MoE, not against a capacity-matched alternative, so the gain cannot be clearly attributed to the MoE design rather than to added capacity. Why no MoE for the polarization branch? The polarization branch does not use MoE, and the paper does not explain why. This is especially puzzling because polarization parameters are claimed to be more vulnerable to degradation than intensity (Sec. 3.1). In that case, degradation-specific routing would seem at least as relevant to the polarization branch.
Questions for authors
- Tab. 1 compares representations on NAFNet only, and the margins are small. Please repeat the comparison within your proposed architecture, ideally on one more backbone, to show the choice of normalized Stokes holds beyond a single network.
- Design motivation. Why extend the intensity branch with MoE instead of simply increasing its depth or width? A capacity-matched baseline is needed, given that your model is already the largest (43.4M). Why is MoE not used in the polarization branch?
7 comments
Response to Reviewer BiFx (Part 2/2): MoE in the intensity and polarization branches (W2 and Q2)
We explain why the intensity branch uses MoE and why the polarization branch remains lightweight, with comparisons to dense refinement and MoE in both branches.
MoE in the intensity branch. We use a mixture of experts (MoE) to increase the capacity of the intensity branch and improve its ability to handle composite degradations and degradations outside the pretraining distribution, such as mosaic artifacts. The parallel design lets us initialize the experts by copying pretrained weights without changing the original branch. At inference, activating only the top-ranked expert limits the added computation.
We compare MoE with a dense refinement module that stacks NAFNet blocks at the end of the network and has a comparable computational cost. The two variants achieve comparable restoration performance, while MoE has lower inference latency (Table R5).
Table R5. Comparison with Ours-Refine and Ours-MoE on PolarCDD for 100k iterations.
| Method | ↑ | ↑ | ↑ | ↑ | ↓ | Params(M)↓ | FLOPs(T)↓ | Latency(ms)↓ |
|---|---|---|---|---|---|---|---|---|
| Ours-Refine | 32.73 | 31.07 | 0.92 | 0.79 | 15.89 | 37.47 | 0.19 | 99.72 |
| Ours-MoE | 32.70 | 31.10 | 0.92 | 0.79 | 15.83 | 43.43 | 0.19 | 86.05 |
Keeping the polarization branch lightweight. We also investigated incorporating a MoE design into the polarization branch. As shown in Table R6, adding MoE to the polarization branch yields no improvement in polarimetric metrics. We attribute this to architectural redundancy: the intensity branch already identifies and models the degradation patterns, while the polarization branch acquires this knowledge via cross-domain transfer for polarization restoration. In this sense, the polarization branch already acts as an extra expert.
Therefore, we keep the polarization branch lightweight as possible, without introducing additional MoE or text-based modulation, and halve the number of its blocks.
Table R6. Comparison with Ours-DualMoE and Ours on the AIO3 setting for 100k iterations.
| Method | ↑ | ↑ | ↑ | ↑ | MAE ↓ |
|---|---|---|---|---|---|
| Ours-DualMoE | 36.05 | 32.19 | 0.94 | 0.78 | 13.44 |
| Ours | 35.83 | 32.21 | 0.93 | 0.78 | 13.40 |
Thank you again for your valuable comments. We have conducted additional experiments and updated the manuscript accordingly. We look forward to your feedback and would be happy to address any further concerns during the discussion period.
Response to Reviewer BiFx (Part 1/2): Choice of polarization representation (W1 and Q1)
Thank you for recognizing the motivation for our work and the value of the benchmark. Our responses are provided below:
We address why we use normalized Stokes, whether its benefits extend from NAFNet to SwinIR, and how it performs across intensity and DoLP levels.
Why we use normalized Stokes. In normalized Stokes, intensity and polarization are theoretically fully decoupled. The network directly predicts the independent polarization components q and u, from which we compute DoLP=q2+u2 and AoP=21atan2(u,q) without using S0. By comparison, S1 and S2 retain intensity information, so predicting [S0,S1,S2] introduces redundancy. Computing DoLP from these predictions requires division by S0, which can amplify noise and degrade performance.
In our dual-branch network, this separation allows the polarization branch to focus on polarization-specific restoration patterns, while the intensity branch models intensity using general restoration priors.
Evaluation across backbones. Our model in the main paper is based on InstructIR, which uses a NAFNet backbone. We also compare the representations on SwinIR (Table R1). The results on both the CNN-based NAFNet and the Transformer-based SwinIR show that [S0,S~1,S~2] is a more effective and stable representation across these backbones.
Performance across intensity and DoLP levels. Tables R2–R4 report polarization metrics stratified by GT intensity, GT DoLP, and input intensity. The normalized Stokes representation [S0,S~1,S~2] yields more stable performance across these levels.
Table R1. SwinIR representations.
Table R2. PSNRp/MAE stratified by GT intensity, with each column corresponding to a different bin center.
Table R3. MAE stratified by GT DoLP, with each column corresponding to a different bin center.
Table R4. PSNRp/MAE stratified by LQ intensity, with each column corresponding to a different bin center.