Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision
원문 초록
Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost. However, we observe that previous unpaired image dehazing approaches tend to suffer from performance degradation near depth borders, where depth tends to vary abruptly. Hence, we propose to anneal the depth border degradation in unpaired image dehazing with cyclic perceptual-depth supervision. Coupled with the dual-path feature re-using backbones of the generators and discriminators, our model achieves $\mathbf{20.36}$ Peak Signal-to-Noise Ratio (PSNR) on NYU Depth V2 dataset, significantly outperforming its predecessors with reduced Floating Point Operations (FLOPs).
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Forward-only Diffusion Probabilistic Models
Degradation-Aware Feature Perturbation for All-in-One Image Restoration
A Preliminary Study for GPT-4o on Image Restoration
WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing
Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.