Diffusion Models Are Real-Time Game Engines
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915255742889984 |
|---|---|
| author | Valevski, Dani Leviathan, Yaniv Arar, Moab Fruchter, Shlomi |
| author_facet | Valevski, Dani Leviathan, Yaniv Arar, Moab Fruchter, Shlomi |
| contents | We present GameNGen, the first game engine powered entirely by a neural model that also enables real-time interaction with a complex environment over long trajectories at high quality. When trained on the classic game DOOM, GameNGen extracts gameplay and uses it to generate a playable environment that can interactively simulate new trajectories. GameNGen runs at 20 frames per second on a single TPU and remains stable over extended multi-minute play sessions. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters are only slightly better than random chance at distinguishing short clips of the game from clips of the simulation, even after 5 minutes of auto-regressive generation. GameNGen is trained in two phases: (1) an RL-agent learns to play the game and the training sessions are recorded, and (2) a diffusion model is trained to produce the next frame, conditioned on the sequence of past frames and actions. Conditioning augmentations help ensure stable auto-regressive generation over long trajectories, and decoder fine-tuning improves the fidelity of visual details and text. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_14837 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion Models Are Real-Time Game Engines Valevski, Dani Leviathan, Yaniv Arar, Moab Fruchter, Shlomi Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition We present GameNGen, the first game engine powered entirely by a neural model that also enables real-time interaction with a complex environment over long trajectories at high quality. When trained on the classic game DOOM, GameNGen extracts gameplay and uses it to generate a playable environment that can interactively simulate new trajectories. GameNGen runs at 20 frames per second on a single TPU and remains stable over extended multi-minute play sessions. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters are only slightly better than random chance at distinguishing short clips of the game from clips of the simulation, even after 5 minutes of auto-regressive generation. GameNGen is trained in two phases: (1) an RL-agent learns to play the game and the training sessions are recorded, and (2) a diffusion model is trained to produce the next frame, conditioned on the sequence of past frames and actions. Conditioning augmentations help ensure stable auto-regressive generation over long trajectories, and decoder fine-tuning improves the fidelity of visual details and text. |
| title | Diffusion Models Are Real-Time Game Engines |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.14837 |