Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation

TL;DR

This paper introduces FrameCache, a training-free framework for human animation that enhances temporal coherence and visual stability by leveraging causality-consistent reference frames and a novel memory and trajectory alignment strategy.

Contribution

It proposes a novel, training-free causality-consistent reference frame framework with dynamic memory and trajectory alignment for improved long-range human animation.

Findings

Improves temporal coherence and visual stability in human animation.

Seamlessly integrates with diverse diffusion models.

Demonstrates effectiveness on standard benchmarks.

Abstract

Human animation aims to generate temporally coherent and visually consistent videos over long sequences, yet modeling long-range dependencies while preserving frame quality remains challenging. Inspired by the human ability to leverage past observations for interpreting ongoing actions, we propose FrameCache, a training-free, causality-consistent reference frame framework. FrameCache explicitly converts historical generation results into causal guidance through two complementary mechanisms. First, at the reference level, a novel Screen-Cache-Match (SCM) strategy constructs a dynamic, high-quality reference memory, ensuring motion-consistent appearance guidance to reduce identity drift. Second, at the generative level, a Trajectory-Aware Autoregressive Generation (TAAG) mechanism aligns denoising trajectories across adjacent video chunks. This is achieved through an overlap-aware latent propagation and a dual-domain fusion strategy that seamlessly blends low-frequency structural layouts with high-frequency textural details. Extensive experiments on standard benchmarks demonstrate that FrameCache consistently improves temporal coherence and visual stability while integrating seamlessly with diverse diffusion baselines. Code will be made publicly available.