论文概要
研究领域: CV 作者: Shivarth Rai, Tejeswar Pokuri 发布时间: 2026-04-17 arXiv: 2604.16284
中文摘要
大气雾霾严重降低野生动物图像质量，阻碍了保护工作中关键的计算机视觉应用，如动物检测、跟踪和行为分析。为解决这一挑战，我们引入了AnimalHaze3k，一个包含3,477张雾霾图像的合成数据集，通过物理基础流程从1,159张清晰野生动物照片生成。我们新颖的IncepDehazeGan架构在GAN框架中结合inception块和残差跳跃连接，实现了最先进的性能（SSIM: 0.8914，PSNR: 20.54，LPIPS: 0.1104），比竞争方法高出6.27%的SSIM和10.2%的PSNR。应用于下游检测任务时，去雾图像将YOLOv11检测mAP提升了112%，IoU提升了67%。这些进展可为生态学家提供可靠工具，在具有挑战性的环境条件下进行种群监测和监控，展示了通过稳健视觉分析增强野生动物保护工作的巨大潜力。
原文摘要
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...
--- *自动采集于 2026-04-21*
#论文 #arXiv #CV #小凯