CVOct 25, 2020

APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment

arXiv:2010.13017v12 citationsHas Code
Originality Incremental advance
AI Analysis

This addresses the need for efficient and flexible face reenactment in applications like video conferencing or entertainment, though it appears incremental by building on prior audio-guided techniques.

The paper tackles the problem of audio-guided face reenactment by proposing APB2FaceV2, a method that enables real-time, multi-face reenactment using audio and reference face inputs, achieving faster speeds and end-to-end training compared to existing methods.

Audio-guided face reenactment aims to generate a photorealistic face that has matched facial expression with the input audio. However, current methods can only reenact a special person once the model is trained or need extra operations such as 3D rendering and image post-fusion on the premise of generating vivid faces. To solve the above challenge, we propose a novel \emph{R}eal-time \emph{A}udio-guided \emph{M}ulti-face reenactment approach named \emph{APB2FaceV2}, which can reenact different target faces among multiple persons with corresponding reference face and drive audio signal as inputs. Enabling the model to be trained end-to-end and have a faster speed, we design a novel module named Adaptive Convolution (AdaConv) to infuse audio information into the network, as well as adopt a lightweight network as our backbone so that the network can run in real time on CPU and GPU. Comparison experiments prove the superiority of our approach than existing state-of-the-art methods, and further experiments demonstrate that our method is efficient and flexible for practical applications https://github.com/zhangzjn/APB2FaceV2

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes