INFP: Audio-Driven Interactive Head Generation in Dyadic Conversations

TL;DR

This paper introduces INFP, a novel framework for audio-driven interactive head generation in dyadic conversations, enabling realistic, dynamic agent behaviors that switch between speaking and listening based on audio cues.

Contribution

We propose INFP, a new head generation model that dynamically alternates between speaking and listening states guided by dyadic audio, and introduce DyConv, a large-scale conversational dataset.

Findings

Outperforms existing head generation methods in realism and interactivity.

Effectively models dynamic role switching in dyadic conversations.

Demonstrates superior performance through extensive experiments.

Abstract

Imagine having a conversation with a socially intelligent agent. It can attentively listen to your words and offer visual and linguistic feedback promptly. This seamless interaction allows for multiple rounds of conversation to flow smoothly and naturally. In pursuit of actualizing it, we propose INFP, a novel audio-driven head generation framework for dyadic interaction. Unlike previous head generation works that only focus on single-sided communication, or require manual role assignment and explicit role switching, our model drives the agent portrait dynamically alternates between speaking and listening state, guided by the input dyadic audio. Specifically, INFP comprises a Motion-Based Head Imitation stage and an Audio-Guided Motion Generation stage. The first stage learns to project facial communicative behaviors from real-life conversation videos into a low-dimensional motion latent space, and use the motion latent codes to animate a static image. The second stage learns the mapping from the input dyadic audio to motion latent codes through denoising, leading to the audio-driven head generation in interactive scenarios. To facilitate this line of research, we introduce DyConv, a large scale dataset of rich dyadic conversations collected from the Internet. Extensive experiments and visualizations demonstrate superior performance and effectiveness of our method. Project Page: https://grisoon.github.io/INFP/.