Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing
This work addresses image dehazing for computer vision applications, but it is incremental as it builds on existing knowledge distillation and transformer methods.
The paper tackles the problem of image dehazing by addressing the domain gap between synthetic and real-world hazy images and incorporating uncertainty estimation, resulting in improved generalization to real-world scenarios as demonstrated in experiments.
Image dehazing is fundamental yet not well-solved in computer vision. Most cutting-edge models are trained in synthetic data, leading to the poor performance on real-world hazy scenarios. Besides, they commonly give deterministic dehazed images while neglecting to mine their uncertainty. To bridge the domain gap and enhance the dehazing performance, we propose a novel semi-supervised uncertainty-aware transformer network, called Semi-UFormer. Semi-UFormer can well leverage both the real-world hazy images and their uncertainty guidance information. Specifically, Semi-UFormer builds itself on the knowledge distillation framework. Such teacher-student networks effectively absorb real-world haze information for quality dehazing. Furthermore, an uncertainty estimation block is introduced into the model to estimate the pixel uncertainty representations, which is then used as a guidance signal to help the student network produce haze-free images more accurately. Extensive experiments demonstrate that Semi-UFormer generalizes well from synthetic to real-world images.