RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors

by   Rui-Qi Wu, et al.

Existing dehazing approaches struggle to process real-world hazy images owing to the lack of paired real data and robust priors. In this work, we present a new paradigm for real image dehazing from the perspectives of synthesizing more realistic hazy data and introducing more robust priors into the network. Specifically, (1) instead of adopting the de facto physical scattering model, we rethink the degradation of real hazy images and propose a phenomenological pipeline considering diverse degradation types. (2) We propose a Real Image Dehazing network via high-quality Codebook Priors (RIDCP). Firstly, a VQGAN is pre-trained on a large-scale high-quality dataset to obtain the discrete codebook, encapsulating high-quality priors (HQPs). After replacing the negative effects brought by haze with HQPs, the decoder equipped with a novel normalized feature alignment module can effectively utilize high-quality features and produce clean results. However, although our degradation pipeline drastically mitigates the domain gap between synthetic and real data, it is still intractable to avoid it, which challenges HQPs matching in the wild. Thus, we re-calculate the distance when matching the features to the HQPs by a controllable matching operation, which facilitates finding better counterparts. We provide a recommendation to control the matching based on an explainable solution. Users can also flexibly adjust the enhancement degree as per their preference. Extensive experiments verify the effectiveness of our data synthesis pipeline and the superior performance of RIDCP in real image dehazing.


page 6

page 7

page 8

page 10

page 12

page 13

page 14

page 15


DiffLLE: Diffusion-guided Domain Calibration for Unsupervised Low-light Image Enhancement

Existing unsupervised low-light image enhancement methods lack enough ef...

RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs

Blind face restoration aims at recovering high-quality face images from ...

NeRFLiX: High-Quality Neural View Synthesis by Learning a Degradation-Driven Inter-viewpoint MiXer

Neural radiance fields (NeRF) show great success in novel view synthesis...

DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views

Synthesizing novel view images from a few views is a challenging but pra...

From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm

Neural radiance fields (NeRF) have shown great success in novel view syn...

Robust Representation Learning with Feedback for Single Image Deraining

A deraining network may be interpreted as a condition generator. Image d...

URIE: Universal Image Enhancement for Visual Recognition in the Wild

Despite the great advances in visual recognition, it has been witnessed ...

Please sign up or login with your details

Forgot password? Click here to reset