Surprise Forcing: Adaptive Memory and Denoising for Long Video Generation
A new preprint introduces Surprise Forcing, a training-free framework designed to enhance long video generation by adaptively managing memory and denoising steps. The method employs a Surprise-Gated Memory Bank to retain important visual information and a Surprise-Aware Denoising schedule that dynamically skips steps for easier video segments. Experimental results on several benchmarks demonstrate improved long-horizon consistency and visual quality, while maintaining real-time streaming throughput.
Why it matters: This approach addresses major challenges in streaming video generation, enabling longer and more coherent videos without compromising efficiency.
Full story at: arXiv Computer Vision ↗