DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data

TL;DR

DynaVid introduces a novel two-stage video synthesis framework that leverages synthetic optical flow data to improve the realism and controllability of highly dynamic videos, addressing dataset limitations.

Contribution

The paper presents a two-stage framework that decouples motion synthesis from appearance, using synthetic optical flow to enhance dynamic video generation.

Findings

Improves realism in videos with vigorous human motion.

Enhances controllability in camera motion scenarios.

Outperforms existing models on dynamic motion benchmarks.

Abstract

Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A central limitation lies in the scarcity of such examples in commonly used training datasets. To address this, we introduce DynaVid, a video synthesis framework that leverages synthetic motion data in training, which is represented as optical flow and rendered using computer graphics pipelines. This approach offers two key advantages. First, synthetic motion offers diverse motion patterns and precise control signals that are difficult to obtain from real data. Second, unlike rendered videos with artificial appearances, rendered optical flow encodes only motion and is decoupled from appearance, thereby preventing models from reproducing the unnatural look of synthetic videos. Building on this idea, DynaVid adopts a two-stage generation framework: a motion generator first synthesizes motion, and then a motion-guided video generator produces video frames conditioned on that motion. This decoupled formulation enables the model to learn dynamic motion patterns from synthetic data while preserving visual realism from real-world videos. We validate our framework on two challenging scenarios, vigorous human motion generation and extreme camera motion control, where existing datasets are particularly limited. Extensive experiments demonstrate that DynaVid improves the realism and controllability in dynamic motion generation and camera motion control.