SpA-Former: Transformer image shadow detection and removal via spatial attention
TL
TL;DR
An end-to-end SpA-Former to recover a shadow-free image from a single shaded image, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection.
Abstract
In this paper, we propose an end-to-end SpA-Former to recover a shadow-free image from a single shaded image. Unlike traditional methods that require two steps for shadow detection and then shadow removal, the SpA-Former unifies these steps into one, which is a one-stage network capable of directly learning the mapping function between shadows and no shadows, it does not require a separate shadow detection. Thus, SpA-former is adaptable to real image de-shadowing for shadows projected on different semantic regions. SpA-Former consists of transformer layer and a series of joint Fourier transform residual blocks and two-wheel joint spatial attention. The network in this paper is able to handle the task while achieving a very fast processing efficiency. Our code is relased on https://github.com/zhangbaijin/SpA-Former-shadow-removal
References22 items
1
AFFNet: Attention Mechanism Network Based on Fusion Feature for Image Cloud Removal
2
Restormer: Efficient Transformer for High-Resolution Image Restoration
3
CANet: A Context-Aware Network for Shadow Removal
4
RGAN: Rethinking generative adversarial networks for cloud removal
5