Translations:Diffusion Models Are Real-Time Game Engines/54/en
Image Quality. We measure LPIPS (Zhang et al., 2018) and PSNR using the teacher-forcing setup described in Section 2, where we sample an initial state and predict a single frame based on a trajectory of ground-truth past observations. When evaluated over a random holdout of 2048 trajectories taken in 5 different levels, our model achieves a PSNR of and an LPIPS of . The PSNR value is similar to lossy JPEG compression with quality settings of 20-30 (Petric & Milinkovic, 2018). Figure 5 shows examples of model predictions and the corresponding ground truth samples.
