- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper focuses on the design of fundamental visual operators and architectural improvements for image restoration. It investigates whether visual state propagation can move beyond Mamba's one-dimensional sequential scanning and operate directly in two-dimensional image space. To this end, the authors propose a new token mixer, Neighborhood State Interaction (NSI), which enables multi-step state propagation through synchronous neighborhood interactions. It further incorporates input-conditioned interactions, state-dependent retention, and incremental readout to improve propagation efficiency and stability. Overall, the paper addresses a meaningful research problem, and the proposed method has a certain theoretical foundation. However, my main concern is the limited scope of the experimental evaluation.
Critical strengths
-
The research problem is meaningful. The paper rethinks visual state propagation by considering the mismatch between two-dimensional spatial adjacency and one-dimensional scan order. This is a problem with fundamental research significance.
-
The module design is relatively comprehensive. The proposed method combines input-conditioned interactions, state-dependent retention, parameter sharing across propagation steps, and incremental readout. These components are well aligned with the research motivation. In addition, the authors provide a theoretical analysis of the stability of multi-step propagation.
Critical weaknesses
-
The choice of backbone is relatively limited. Although the authors conduct experiments on 3 datasets and 2 image restoration tasks, all experiments are based on the VIVNet backbone. Given that NSI is proposed as a general-purpose token mixer, the lack of evaluation on other network architectures leaves its generalizability across different backbones unclear.
-
The comparisons with other scanning mechanisms are insufficient. The authors mainly compare NSI with VMamba's SS2D and additionally include MaIR and Spatial-Mamba. However, only SS2D is evaluated on all 3 datasets, while MaIR and Spatial-Mamba are evaluated only on O-HAZE, which contains just 5 test images. Furthermore, the paper lacks quantitative comparisons with other relevant scanning mechanisms.
Questions for authors
-
Can NSI preserve Mamba's advantages in long-range dependency modeling? With the default 5 propagation steps, a single NSI module has a direct propagation range of only 11 × 11. By replacing sequential scanning with local neighborhood interactions, NSI may lose one of Mamba's key advantages: efficient long-range dependency modeling. Could the authors further discuss this potential limitation?
-
Does NSI generalize across different backbones? The current experiments mainly demonstrate that NSI outperforms SS2D within VIVNet, but it remains unclear whether similar improvements can be achieved with other network architectures.
-
Could the authors provide additional comparisons with other scanning mechanisms? I suggest including more comparisons with different scanning mechanisms to further validate the effectiveness of NSI relative to alternative scanning strategies.
9 comments
Follow-up: have our responses addressed your concerns?
Dear Reviewer DDai,
Thank you again for your thoughtful review and for your recognition of the research problem. As the discussion period closes on November 18 (AoE), we would like to check whether our responses and the revised paper have addressed your concerns. Since our first response, we have also trained EAMamba and C2SSM under VIVNet's full Haze4K schedule: on the 1,000-image test set NSI is above both, including EAMamba, which was slightly ahead on the five-image O-HAZE (Table 22). In particular:
- A second backbone, the native Mamba network EVSSM (Table 4; Appendix E).
- Additional scan mechanisms on the 1,000-image Haze4K test set (Table 22), where NSI is the most accurate at the lowest MACs.
If any point remains unclear, we would be glad to clarify during the discussion period. If you find that your concerns have been resolved, we would be grateful if you would consider updating your assessment.
Response to Reviewer DDai (Part 2 of 2): W2/Q3
W2, Q3 – Comparisons with other scanning mechanisms
Weakness 2: "The comparisons with other scanning mechanisms are insufficient. [...] only SS2D is evaluated on all 3 datasets, while MaIR and Spatial-Mamba are evaluated only on O-HAZE, which contains just 5 test images. Furthermore, the paper lacks quantitative comparisons with other relevant scanning mechanisms."
Question 3: "Could the authors provide additional comparisons with other scanning mechanisms? [...]"
A3. Thank you for this suggestion. We added four scanning mechanisms and evaluated them on the 1,000-image Haze4K test set under VIVNet's full training schedule (Table R1): window-ordered scans (Local4, as in LocalMamba), eight-direction scans (RS8, as in RS-Mamba), EAMamba and C2SSM.
Table R1: Scanning mechanisms under VIVNet's full Haze4K schedule (seed 42; 1,000 test images; Table 22, p. 34).
| Mixer | PSNR (dB) | SSIM | MACs (G) |
|---|---|---|---|
| EAMamba | 35.32 | 0.9908 | 27.8 |
| SS2D | 35.16 | 0.9902 | 36.7 |
| RS8 | 35.07 | 0.9900 | 51.7 |
| C2SSM | 34.24 | 0.9895 | 34.5 |
| Local4 | 33.61 | 0.9877 | 36.7 |
| Ours | 35.51 | 0.9922 | 25.6 |
NSI is the most accurate of these scans at the lowest MACs. The comparison also shows how strongly a scan depends on its routes: RS8 is within 0.1 dB of SS2D, whereas Local4, which keeps every SS2D component and changes only two of its four routes, is 1.55 dB lower. NSI has no route to choose.
We also retrained the same four scans on O-HAZE with the main protocol (Table 26, p. 36). They reach 26.67, 26.38, 26.94 and 26.86 dB, against 26.78 dB for NSI. With five test images and one seed, differences of 0.1–0.2 dB are within the seed variation of Table 2, so the 1,000-image Haze4K comparison above is the more reliable one. In addition, SS2D is now compared over three seeds on all three main datasets (Tables 1–2, pp. 7–8).
For MaIR and Spatial-Mamba, we verified each transfer against the official code (forward error 0, gradients within 1e-6, all 22 locations running the official modules; Appendix I, p. 35), and showed that their low O-HAZE scores come mainly from the evaluation resolution (Appendix D.3, p. 32).
Revision: Table 22 and Appendix F (pp. 33–34); Table 26 and Appendix I (pp. 35–36); Appendix D.3 (p. 32).
Thank you again for your encouraging assessment of the problem and for suggestions that broadened our evaluation. We would be glad to provide any further clarification before the discussion period closes.
Response to Reviewer DDai (Part 1 of 2): Q1 and W1/Q2
Thank you very much for your thoughtful review, and for recognizing both the significance of the research problem and how the module design follows from it. We have revised the manuscript based on your feedback. Below, we quote each point and describe the revision and where it appears. Please let us know whether we have addressed your concerns.
Q1 – Long-range dependency modelingA1. Thank you for raising this. A single NSI module does not keep Mamba's global path: with K=5, its direct reach is 11×11 positions at that module's resolution, and we now state this trade-off in the conclusion (Section 6, p. 10). What NSI keeps from Mamba is selective state propagation, with selection that depends on the input and on the evolving state. What it gives up is the ordering of that propagation along a 1D sequence.
In the network, long-range context comes from composition across scales and blocks. The theoretical receptive field of VIVNet-B with NSI is 776 pixels, and the measured ERF is wide and nearly isotropic (Table R1).
Table R1: ERF over 47 test images and three seeds (Table 15, p. 28).
On the tasks we tested, this did not cost accuracy: under VIVNet's full Haze4K schedule NSI is 0.35 dB above SS2D, and on GoPro at 200K updates it is 0.12 dB above (Table 3, p. 8). The number of steps K trades reach against cost without affecting stability (Table 5(a), p. 9). Combining depth-indexed propagation with a lightweight global path is a natural extension that we leave to future work.
W1, Q2 – Generalization across backbonesA2. Thank you for this suggestion. We added a second backbone: EVSSM (CVPR 2025), a native Mamba deblurring network. We replaced all 48 of its SS2D mixers with NSI and kept every other component. NSI reaches 31.29 vs. 30.88 dB with 24.4% fewer MACs and 25% fewer parameters, and is better on 866 of 1,111 frames and on 10 of 11 test videos (two-sided video-level sign test, p=0.012). Our evaluation of the released EVSSM checkpoint gives 34.53 dB against the 34.5 dB reported.
Since all our evidence is on restoration, we have also revised the title to end with "for Image Restoration", and we no longer present NSI as a general-purpose token mixer.
Revision: Table 4 (p. 8) and Appendix E (p. 33); title, abstract and Section 6 (p. 10).