CVOct 24, 2024

You Only Look Around: Learning Illumination Invariant Feature for Low-light Object Detection

arXiv:2410.18398v130 citationsh-index: 9Has CodeNIPS
Originality Highly original
AI Analysis

This addresses the problem of reliable object detection in varying lighting conditions for applications like autonomous driving or surveillance, representing a novel method for a known bottleneck.

The paper tackles object detection in low-light scenarios by learning illumination-invariant features using the Lambertian image formation model, resulting in significant improvements in detection tasks and promising performance in well-lit and over-lit conditions.

In this paper, we introduce YOLA, a novel framework for object detection in low-light scenarios. Unlike previous works, we propose to tackle this challenging problem from the perspective of feature learning. Specifically, we propose to learn illumination-invariant features through the Lambertian image formation model. We observe that, under the Lambertian assumption, it is feasible to approximate illumination-invariant feature maps by exploiting the interrelationships between neighboring color channels and spatially adjacent pixels. By incorporating additional constraints, these relationships can be characterized in the form of convolutional kernels, which can be trained in a detection-driven manner within a network. Towards this end, we introduce a novel module dedicated to the extraction of illumination-invariant features from low-light images, which can be easily integrated into existing object detection frameworks. Our empirical findings reveal significant improvements in low-light object detection tasks, as well as promising results in both well-lit and over-lit scenarios. Code is available at \url{https://github.com/MingboHong/YOLA}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes