Single Image Super-Resolution via Bivariate `A Trous Wavelet Diffusion

2026-03-07

AI Summary

This work addresses the challenge of inconsistent structures and artifacts in single-image super-resolution, which often arise from the ambiguity of low-resolution observations when recovering high-frequency details. To this end, the authors propose BATDiff, an unsupervised bivariate à trous wavelet diffusion model that constructs an undecimated multiscale representation at full spatial resolution via the à trous wavelet transform. A novel bivariate cross-scale module is introduced to explicitly model parent-child dependencies between adjacent scales, enabling structure-guided, progressive restoration of high-frequency components during the diffusion process. Extensive experiments demonstrate that BATDiff outperforms both existing diffusion-based and non-diffusion-based methods on standard benchmarks, achieving significant improvements in image sharpness, structural consistency, fidelity, and perceptual quality.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Unsupervised & Self-Supervised Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

The effectiveness of super resolution (SR) models hinges on their ability to recover high frequency structure without introducing artifacts. Diffusion based approaches have recently advanced the state of the art in SR. However, most diffusion based SR pipelines operate purely in the spatial domain, which may yield high frequency details that are not well supported by the underlying low resolution evidence. On the other hand, unlike supervised SR models that may inject dataset specific textures, single image SR relies primarily on internal image statistics and can therefore be less prone to dataset-driven hallucinations; nevertheless, ambiguity in the LR observation can still lead to inconsistent high frequency details. To tackle this problem, we introduce BATDiff, an unsupervised Bivariate A trous Wavelet Diffusion model designed to provide structured cross scale guidance during the generative process. BATDiff employs an a Trous wavelet transform that constructs an undecimated multiscale representation in which high frequency components are progressively revealed while the full spatial resolution is preserved. As the core inference mechanism, BATDiff includes a bivariate cross scale module that models parent child dependencies between adjacent scales. It improves high frequency coherence and reduces mismatch artifacts in diffusion based SR. Experiments on standard benchmarks demonstrate that BATDiff produces sharper and more structurally consistent reconstructions than existing diffusion and non diffusion baselines, achieving improvements in fidelity and perceptual quality.

Problem

• Single Image Super-Resolution
• High Frequency Coherence
• Artifact Reduction
• Cross-scale Consistency
• Unsupervised Reconstruction

Innovation

• Bivariate a Trous Wavelet
• Diffusion Model
• Unsupervised Super-Resolution
• Cross-Scale Dependency
• Multiscale Representation