Enhancing Hazy Wildlife Imagery: AnimalHaze3k and IncepDehazeGan
2026-04-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a large set of fake hazy animal photos to help improve computer programs that clear up blurry images caused by fog. They developed a new method called IncepDehazeGan that cleans these hazy pictures better than other existing methods. This clearer image helps animal detection software find animals more accurately. Their work can help scientists monitor wildlife even in foggy or hazy conditions.
atmospheric hazewildlife imageryimage dehazingGAN (Generative Adversarial Network)Inception blocksresidual connectionsSSIMPSNRYOLO object detectionmAP (mean Average Precision)
Authors
Shivarth Rai, Tejeswar Pokuri
Abstract
Atmospheric haze significantly degrades wildlife imagery, impeding computer vision applications critical for conservation, such as animal detection, tracking, and behavior analysis. To address this challenge, we introduce AnimalHaze3k a synthetic dataset comprising of 3,477 hazy images generated from 1,159 clear wildlife photographs through a physics-based pipeline. Our novel IncepDehazeGan architecture combines inception blocks with residual skip connections in a GAN framework, achieving state-of-the-art performance (SSIM: 0.8914, PSNR: 20.54, and LPIPS: 0.1104), delivering 6.27% higher SSIM and 10.2% better PSNR than competing approaches. When applied to downstream detection tasks, dehazed images improved YOLOv11 detection mAP by 112% and IoU by 67%. These advances can provide ecologists with reliable tools for population monitoring and surveillance in challenging environmental conditions, demonstrating significant potential for enhancing wildlife conservation efforts through robust visual analytics.