Seeing Text in the Dark: Algorithm and Benchmark

TL;DR

This paper introduces a single-stage text localization method for dark environments that avoids low-light image enhancement, using a constrained learning module to preserve spatial features, achieving state-of-the-art results.

Contribution

A novel single-stage approach with a constrained learning module for low-light text localization, eliminating the need for low-light image enhancement and improving spatial feature preservation.

Findings

Achieves state-of-the-art results on low-light text datasets

Performs comparably on normal-light datasets

Introduces a new low-light text dataset

Abstract

Localizing text in low-light environments is challenging due to visual degradations. Although a straightforward solution involves a two-stage pipeline with low-light image enhancement (LLE) as the initial step followed by detector, LLE is primarily designed for human vision instead of machine and can accumulate errors. In this work, we propose an efficient and effective single-stage approach for localizing text in dark that circumvents the need for LLE. We introduce a constrained learning module as an auxiliary mechanism during the training stage of the text detector. This module is designed to guide the text detector in preserving textual spatial features amidst feature map resizing, thus minimizing the loss of spatial information in texts under low-light visual degradations. Specifically, we incorporate spatial reconstruction and spatial semantic constraints within this module to ensure the text detector acquires essential positional and contextual range knowledge. Our approach enhances the original text detector's ability to identify text's local topological features using a dynamic snake feature pyramid network and adopts a bottom-up contour shaping strategy with a novel rectangular accumulation technique for accurate delineation of streamlined text features. In addition, we present a comprehensive low-light dataset for arbitrary-shaped text, encompassing diverse scenes and languages. Notably, our method achieves state-of-the-art results on this low-light dataset and exhibits comparable performance on standard normal light datasets. The code and dataset will be released.