OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs

ArXi:2412.09465v3 Announce Type: replace Recent advances in diffusion and flow-based generative models have nstrated remarkable success in image restoration tasks, achieving superior perceptual quality compared to traditional deep learning approaches. However, these methods either require numerous sampling steps to generate high-quality images, resulting in significant computational overhead, or rely on common model distillation, which usually imposes a fixed fidelity-realism trade-off and thus lacks flexibility. In this paper, we