- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes Scene-Preserving Counterfactual Diffusion (SPCD) for low-light video restoration. The method formulates restoration as an instance-specific counterfactual problem, aiming to modify relevant degradation factors while preserving the factual scene. SPCD uses diffusion-score differences to identify target-specific intervention factors and sparse temporal propagation structures, which subsequently guide counterfactual reverse diffusion. Experiments on real-world and controlled benchmarks demonstrate competitive restoration performance, particularly under dynamically varying degradation conditions.
Critical strengths
- The paper addresses an interesting problem by considering target-specific degradation factors and temporal propagation structures rather than relying solely on predefined temporal dependencies.
- The proposed framework integrates scene-preserving diffusion inversion, intervention selection, and sparse propagation structure inference into a coherent restoration pipeline.
- The experimental evaluation is relatively comprehensive. In particular, the controlled degradation experiments and cardinality-matched sparsification comparisons provide useful evidence for the effectiveness of the proposed structure-selection mechanism.
Critical weaknesses
-
Insufficient justification of the causal interpretation. The proposed diffusion-score discrepancies measure the sensitivity of the denoising model to changes in conditioning variables, but such sensitivity does not necessarily correspond to genuine causal effects. Although the paper provides validation under controlled degradation mechanisms, the extent to which the inferred structures capture meaningful causal dependencies in real-world videos remains unclear.
-
Gap between the theoretical minimal-intervention formulation and its practical implementation. The theoretical objective seeks a minimal intervention subset satisfying a joint response constraint, whereas the implemented method independently thresholds singleton intervention responses. This approximation may fail when degradation factors interact, and the paper does not establish conditions under which the heuristic recovers or approximates the intended minimal intervention set.
-
Limited theoretical support for the diffusion-score surrogate. The connection between squared noise-prediction differences and KL divergence is established for individual Gaussian reverse transitions with shared variance. However, the method uses only a few score evaluations along a fixed inversion trajectory to approximate divergences between complete counterfactual response distributions. The validity of this approximation for intervention and propagation selection requires further justification.
-
Missing comparisons with simpler adaptive conditioning mechanisms. The paper includes several useful internal baselines, but it does not directly compare SPCD with a capacity-matched adaptive attention or gating mechanism using the same diffusion backbone. Such a comparison is important to determine whether explicit counterfactual response evaluation offers benefits beyond conventional learned condition selection.
Questions for authors
- Under what assumptions does singleton intervention thresholding approximate the joint minimal-intervention objective, particularly when degradation factors interact?
- Can the authors explain why removing inversion initialization improves GT-PSNR in Table 4(a), and provide additional evidence that inversion improves scene preservation?