Scene-Preserving Counterfactual Diffusion for Low-Light Video Restoration

Multi-frame low-light restoration typically operates over predefined candidate temporal dependencies, yet relevant degradation factors and propagation paths may vary across targets as imaging conditions change. We formulate restoration as a scene-preserving counterfactual problem, asking how the target would appear if relevant degradation conditions shifted toward normal light while the factual scene remained fixed. We propose Scene-Preserving Counterfactual Diffusion (SPCD), which infers a target-specific intervention structure. Using controlled responses and diffusion-score differences, SPCD selects a minimal set of degradation factors and propagation paths to guide reverse diffusion toward normal light. Experiments on real-world and controlled benchmarks across multiple dynamic regimes demonstrate improved quality. Code will be released after acceptance.