Exploring Reliable Matching with Phase Enhancement for Night-time Semantic Segmentation
This addresses the problem of accurate night-time semantic segmentation for applications such as autonomous driving, though it appears incremental as it builds on existing segmentation methods with specific enhancements for low-light conditions.
The paper tackles semantic segmentation of night-time images by proposing NightFormer, an end-to-end approach that avoids fitting night-time data into day-time distributions, achieving favorable performance against state-of-the-art methods on benchmarks like NightCity, BDD, and Cityscapes.
Semantic segmentation of night-time images holds significant importance in computer vision, particularly for applications like night environment perception in autonomous driving systems. However, existing methods tend to parse night-time images from a day-time perspective, leaving the inherent challenges in low-light conditions (such as compromised texture and deceiving matching errors) unexplored. To address these issues, we propose a novel end-to-end optimized approach, named NightFormer, tailored for night-time semantic segmentation, avoiding the conventional practice of forcibly fitting night-time images into day-time distributions. Specifically, we design a pixel-level texture enhancement module to acquire texture-aware features hierarchically with phase enhancement and amplified attention, and an object-level reliable matching module to realize accurate association matching via reliable attention in low-light environments. Extensive experimental results on various challenging benchmarks including NightCity, BDD and Cityscapes demonstrate that our proposed method performs favorably against state-of-the-art night-time semantic segmentation methods.