SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video Generation

TL;DR

SpriteHand is a real-time autoregressive video generation framework that synthesizes diverse, realistic hand-object interactions across various object types and motions, surpassing traditional physics engines in flexibility and visual quality.

Contribution

The paper introduces SpriteHand, a novel autoregressive model capable of real-time, versatile hand-object interaction video synthesis with improved realism and coherence over existing methods.

Findings

Supports 18 FPS at 640x368 resolution

Achieves high visual realism and interaction fidelity

Handles a wide range of object types and motions

Abstract

Modeling and synthesizing complex hand-object interactions remains a significant challenge, even for state-of-the-art physics engines. Conventional simulation-based approaches rely on explicitly defined rigid object models and pre-scripted hand gestures, making them inadequate for capturing dynamic interactions with non-rigid or articulated entities such as deformable fabrics, elastic materials, hinge-based structures, furry surfaces, or even living creatures. In this paper, we present SpriteHand, an autoregressive video generation framework for real-time synthesis of versatile hand-object interaction videos across a wide range of object types and motion patterns. SpriteHand takes as input a static object image and a video stream in which the hands are imagined to interact with the virtual object embedded in a real-world scene, and generates corresponding hand-object interaction effects in real time. Our model employs a causal inference architecture for autoregressive generation and leverages a hybrid post-training approach to enhance visual realism and temporal coherence. Our 1.3B model supports real-time streaming generation at around 18 FPS and 640x368 resolution, with an approximate 150 ms latency on a single NVIDIA RTX 5090 GPU, and more than a minute of continuous output. Experiments demonstrate superior visual quality, physical plausibility, and interaction fidelity compared to both generative and engine-based baselines.