Figure 2. The framework of GDPO, which consists of two core stages: (a) advantage calculation and (b) policy optimization. Firstly, we
employ a pre-trained one-step Real-ISR model as the reference model to generate a group of diverse outputs by injecting different random
noises. Subsequently, we compute the advantage A for each sample by evaluating its reward with our designed attribute-aware reward
functions and converting these rewards into group-relative advantages. In the policy optimization stage, we feed these samples along with
noises into both the policy model and the reference ISR model, and update the parameters of the policy ISR model by minimizing the
proposed GDPO loss, steering it to favor generating high-reward samples.