Launching the next phase of our 1X World Model Challenge: Sampling.
This stage focuses on predicting future video frames with high accuracy, using methods like GANs and Diffusion Models to generate coherent scene continuations.
To be competitive, submissions should achieve a PSNR of around 26.5 or above. We will open our evaluation server for submissions and release our metric in March 2025. The top entry will be announced in June 2025 and will receive a $10,000 prize.
For submissions and questions, reach out via [email protected].
https://lnkd.in/dAPyrEdS