Mapping License Plate Recoverability Under Extreme Viewing Angles for Oppor-tunistic Urban Sensing

TL;DR

This paper introduces recoverability maps to quantify the limits of license plate recognition from extreme viewing angles in urban sensing, demonstrating that sensing geometry primarily constrains recoverability.

Contribution

The paper presents a novel, task-agnostic method combining synthetic degradation sweeps and summary measures to map recoverability boundaries in degraded imagery.

Findings

Best model recovers 93% of the parameter space.

Sensing geometry, not architecture, limits recovery.

Restoration architectures perform similarly across the parameter space.

Abstract

Urban environments contain many imaging sensors built for specific purposes, including ATM, body-worn, CCTV, and dashboard cameras. Under the opportunistic sensing paradigm, these sensors can be repurposed for secondary inference tasks such as license plate recognition. Yet objects of interest in such imagery are often noisy, low-resolution, and captured from extreme viewpoints. Recent advances in AI-based restoration can recover use-ful information even from severely degraded images. A central challenge is determining which distortion parame-ters allow reliable recovery and which lead to inference failure. This paper introduces recoverability maps, a task-agnostic method for quantifying this boundary. The method combines a dense synthetic sweep of degrada-tion parameters with two summary measures: boundary area-under-curve, which estimates the recoverable frac-tion of the parameter space, and a reliability score, which captures the frequency and severity of failures within that region. We demonstrate the method on license plate recognition from highly angled views under realistic camera artifacts. Several restoration architectures are trained and evaluated, including U-Net, Restormer, Pix2Pix, and SR3 diffusion. The best model recovers about 93% of the parameter space. Similar results across models sug-gest that sensing geometry, rather than architecture, sets the limit of recovery.