Super-Resolution with Structured Motion

2025-05-21

AI Summary

This work addresses two fundamental limitations in single-image super-resolution (SR): restricted upscaling factors under practical imaging constraints and the conventional treatment of motion blur as a nuisance artifact. We propose a novel, theoretically grounded single-frame SR framework that fundamentally reinterprets motion blur. Our key contribution is the first theoretical proof that structured, pseudo-random motion blur encodes beneficial prior information—rather than mere degradation—for high-fidelity reconstruction. Integrating high-precision motion trajectory modeling, sparse image priors, and convex optimization via ℓ₁-minimization, we formulate a verifiable box-car convolutional inversion model enabling provably distortion-free recovery of sparse signals. Evaluated on both synthetic and real-world data, our motion-aware imaging framework achieves high-magnification SR (>4×) from a single low-resolution input—surpassing the resolution ceiling of conventional reconstruction methods.

Technology Category

• Computer Vision: Motion & Tracking
• Reasoning under Uncertainty: Stochastic Optimization
• Search and Optimization: Non-convex Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

We consider the limits of super-resolution using imaging constraints. Due to various theoretical and practical limitations, reconstruction-based methods have been largely restricted to small increases in resolution. In addition, motion-blur is usually seen as a nuisance that impedes super-resolution. We show that by using high-precision motion information, sparse image priors, and convex optimization, it is possible to increase resolution by large factors. A key operation in super-resolution is deconvolution with a box. In general, convolution with a box is not invertible. However, we obtain perfect reconstructions of sparse signals using convex optimization. We also show that motion blur can be helpful for super-resolution. We demonstrate that using pseudo-random motion it is possible to reconstruct a high-resolution target using a single low-resolution image. We present numerical experiments with simulated data and results with real data captured by a camera mounted on a computer controlled stage.

Problem

• Overcoming small resolution limits in super-resolution methods
• Utilizing motion blur as an aid for super-resolution
• Achieving high-resolution reconstruction from single low-resolution images

Innovation

• High-precision motion information for super-resolution
• Sparse image priors with convex optimization
• Pseudo-random motion aids single-image reconstruction