A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
The 2022 IEEE Transactions on Games Outstanding Paper Award
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
CAMAL adds an auxiliary regularizer during training that aligns model attention with segmentation masks to improve both spatial accuracy and causal faithfulness of attention in deep learning and deep reinforcement learning vision models.
citing papers explorer
-
Diffusion Models Are Real-Time Game Engines
A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.
-
CAMAL: Improving Attention Alignment and Faithfulness with Segmentation Masks
CAMAL adds an auxiliary regularizer during training that aligns model attention with segmentation masks to improve both spatial accuracy and causal faithfulness of attention in deep learning and deep reinforcement learning vision models.