4KDehazeFlow: Ultra-High-Definition Image Dehazing via Flow Matching
This work addresses image quality issues in computer vision for applications like photography or autonomous systems, but it appears incremental as it builds on existing deep learning and flow-based techniques.
The paper tackles the problem of ultra-high-definition image dehazing by proposing 4KDehazeFlow, a method based on Flow Matching and a Haze-Aware vector field, which achieves a 2dB PSNR increase and outperforms seven state-of-the-art methods in dense haze and color fidelity.
Ultra-High-Definition (UHD) image dehazing faces challenges such as limited scene adaptability in prior-based methods and high computational complexity with color distortion in deep learning approaches. To address these issues, we propose 4KDehazeFlow, a novel method based on Flow Matching and the Haze-Aware vector field. This method models the dehazing process as a progressive optimization of continuous vector field flow, providing efficient data-driven adaptive nonlinear color transformation for high-quality dehazing. Specifically, our method has the following advantages: 1) 4KDehazeFlow is a general method compatible with various deep learning networks, without relying on any specific network architecture. 2) We propose a learnable 3D lookup table (LUT) that encodes haze transformation parameters into a compact 3D mapping matrix, enabling efficient inference through precomputed mappings. 3) We utilize a fourth-order Runge-Kutta (RK4) ordinary differential equation (ODE) solver to stably solve the dehazing flow field through an accurate step-by-step iterative method, effectively suppressing artifacts. Extensive experiments show that 4KDehazeFlow exceeds seven state-of-the-art methods. It delivers a 2dB PSNR increase and better performance in dense haze and color fidelity.