Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation

TL;DR

This paper introduces MCNet, a novel memory-augmented network that learns a global facial representation space to improve the fidelity and identity preservation in talking head video generation, especially during complex motions.

Contribution

The paper proposes a new implicit identity representation conditioned memory network with a unified facial meta-memory bank and a query mechanism for enhanced talking head synthesis.

Findings

Outperforms previous state-of-the-art methods on VoxCeleb1 and CelebV datasets.

Effectively compensates for occluded regions and expression variations.

Learns a comprehensive facial memory for high-fidelity video generation.

Abstract

Talking head video generation aims to animate a human face in a still image with dynamic poses and expressions using motion information derived from a target-driving video, while maintaining the person's identity in the source image. However, dramatic and complex motions in the driving video cause ambiguous generation, because the still source image cannot provide sufficient appearance information for occluded regions or delicate expression variations, which produces severe artifacts and significantly degrades the generation quality. To tackle this problem, we propose to learn a global facial representation space, and design a novel implicit identity representation conditioned memory compensation network, coined as MCNet, for high-fidelity talking head generation.~Specifically, we devise a network module to learn a unified spatial facial meta-memory bank from all training samples, which can provide rich facial structure and appearance priors to compensate warped source facial features for the generation. Furthermore, we propose an effective query mechanism based on implicit identity representations learned from the discrete keypoints of the source image. It can greatly facilitate the retrieval of more correlated information from the memory bank for the compensation. Extensive experiments demonstrate that MCNet can learn representative and complementary facial memory, and can clearly outperform previous state-of-the-art talking head generation methods on VoxCeleb1 and CelebV datasets. Please check our \href{https://github.com/harlanhong/ICCV2023-MCNET}{Project}.