CausalSR: Structural Causal Model-Driven Super-Resolution with Counterfactual Inference

TL;DR

This paper introduces a causal inference-based framework for super-resolution that models degradation processes, enabling more accurate and interpretable image restoration, especially under complex degradation scenarios.

Contribution

It formulates super-resolution using structural causal models and proposes a counterfactual learning strategy for improved, invariant image restoration.

Findings

Achieves 0.86-1.21dB PSNR improvements over state-of-the-art methods.

Demonstrates the effectiveness of causal reasoning in complex degradation scenarios.

Provides interpretable insights into the image restoration process.

Abstract

Physical and optical factors interacting with sensor characteristics create complex image degradation patterns. Despite advances in deep learning-based super-resolution, existing methods overlook the causal nature of degradation by adopting simplistic black-box mappings. This paper formulates super-resolution using structural causal models to reason about image degradation processes. We establish a mathematical foundation that unifies principles from causal inference, deriving necessary conditions for identifying latent degradation mechanisms and corresponding propagation. We propose a novel counterfactual learning strategy that leverages semantic guidance to reason about hypothetical degradation scenarios, leading to theoretically-grounded representations that capture invariant features across different degradation conditions. The framework incorporates an adaptive intervention mechanism with provable bounds on treatment effects, allowing precise manipulation of degradation factors while maintaining semantic consistency. Through extensive empirical validation, we demonstrate that our approach achieves significant improvements over state-of-the-art methods, particularly in challenging scenarios with compound degradations. On standard benchmarks, our method consistently outperforms existing approaches by significant margins (0.86-1.21dB PSNR), while providing interpretable insights into the restoration process. The theoretical framework and empirical results demonstrate the fundamental importance of causal reasoning in understanding image restoration systems.