Sign In
insight - Shadow Removal
Adaptive Attention-Driven Self and Soft Shadow Removal using Vision Transformer Similarity
DeS3, a diffusion-based method, removes hard, soft, and self shadows from a single image using adaptive attention and Vision Transformer similarity to preserve object structures.
ShadowMaskFormer: An Efficient Transformer-based Framework for Shadow Removal
ShadowMaskFormer, a transformer-based framework, efficiently removes shadows from images by incorporating shadow mask information in the early patch embedding stage.