From Fog to Failure: The Unintended Consequences of Dehazing on Object Detection in Clear Images
This addresses the challenge of balancing enhancement and detection in computer vision pipelines, with incremental insights for hybrid system design.
The study tackled the problem of integrating dehazing into object detection, finding that while effective in foggy conditions, it unexpectedly degrades performance on clear images, highlighting a need for selective preprocessing.
This study explores the challenges of integrating human visual cue-based dehazing into object detection, given the selective nature of human perception. While human vision adapts dynamically to environmental conditions, computational dehazing does not always enhance detection uniformly. We propose a multi-stage framework where a lightweight detector identifies regions of interest (RoIs), which are then improved via spatial attention-based dehazing before final detection by a heavier model. Though effective in foggy conditions, this approach unexpectedly degrades the performance on clear images. We analyze this phenomenon, investigate possible causes, and offer insights for designing hybrid pipelines that balance enhancement and detection. Our findings highlight the need for selective preprocessing and challenge assumptions about universal benefits from cascading transformations.