Feature separation and non-shadow information-guided shadow removal network
To tackle the performance bottlenecks and color deviation issues stemming from current shadow removal methods,a feature separation and non-shadow information guided shadow removal network(FSNIG-ShadowNet)was constructed.In the separation and reconstruction stage,the shadow image was separated into direct light and ambient light using self-reconstruction supervision,with decoupling of lighting types and reflectance.Subsequently,a decoder was employed to re-couple the separated features to yield shadow-free images.In the refinement stage,the network fo-cused on the adjacent regions of shadow and non-shadow,incorporating a local region adaptive normalization module to transfer the color priors of local non-shadow region to shadow regions for mitigating color deviation between the two re-gions.Experimental results demonstrate that the proposed FSNIG-ShadowNet achieves competitive results compared to other state-of-the-art methods.
国家科技期刊平台
NSTL
万方数据
