MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation
Zhejiang Lab（之江实验室）；Li Auto（理想汽车）；Harbin Institute of Technology（哈尔滨工业大学）；Zhejiang University（浙江大学）；Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences（中国科学院大学杭州高等研究院）
说话虚拟人生成已在精确音频同步方面取得显著进展。然而，制作逼真的说话头部视频需要捕捉广泛的情感和细微的面部表情。当前方法面临根本性挑战：a）缺乏用于建模单一基本情感表情的框架，这限制了复合情感等复杂情感的生成；b）缺乏富含人类情感表情的综合数据集，从而限制了模型的潜力。为应对这些挑战，我们提出以下创新：1）情感专家混合（Mixture of Emotion Experts，MoEE）模型，该模型解耦六种基本情感，以实现单一情感状态和复合情感状态的精确合成；2）DH-FaceEmoVid-150数据集，经过专门构建，包含六种常见人类情感表情以及四种复合情感，从而拓展情感驱动模型的训练潜力。此外，为提升情感控制的灵活性，我们提出一个情感到潜变量模块，该模块利用多模态输入，对齐音频、文本和标签等多种控制信号，以确保控制输入更加多样，并实现仅使用音频控制情感的能力。通过大量定量和定性评估，我们证明MoEE框架结合DH-FaceEmoVid-150数据集，在生成复杂情感表情和细腻面部细节方面表现出色，在该领域树立了新的基准。这些数据集将公开发布。
英文摘要：
The generation of talking avatars has achieved significant advancements in precise audio synchronization. However, crafting lifelike talking head videos requires capturing a broad spectrum of emotions and subtle facial expressions. Current methods face fundamental challenges: a) the absence of frameworks for modeling single basic emotional expressions, which restricts the generation of complex emotions such as compound emotions; b) the lack of comprehensive datasets rich in human emotional expressions, which limits the potential of models. To address these challenges, we propose the following innovations: 1) the Mixture of Emotion Experts (MoEE) model, which decouples six fundamental emotions to enable the precise synthesis of both singular and compound emotional states; 2) the DH-FaceEmoVid-150 dataset, specifically curated to include six prevalent human emotional expressions as well as four types of compound emotions, thereby expanding the training potential of emotion-driven models. Furthermore, to enhance the flexibility of emotion control, we propose an emotion-to-latents module that leverages multimodal inputs, aligning diverse control signals-such as audio, text, and labels-to ensure more varied control inputs as well as the ability to control emotions using audio alone. Through extensive quantitative and qualitative evaluations, we demonstrate that the MoEE framework, in conjunction with the DH-FaceEmoVid-150 dataset, excels in generating complex emotional expressions and nuanced facial details, setting a new benchmark in the field. These datasets will be publicly released.
Animating portraits using speech has received growing attention in recent years, with various creative and practical use cases. An ideal generated video should have good lip sync with the audio, natural facial expressions and head motions, and high frame quality. In this work, we present SPACE, which uses speech and a single image to generate high-resolution, and expressive videos with realistic head pose, without requiring a driving video. It uses a multi-stage approach, combining the controllability of facial landmarks with the high-quality synthesis power of a pretrained face generator. SPA…
National Lab of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；North China University of Technology（北方工业大学）
Image matting plays an important role in image and video editing. However, the formulation of image matting is inherently ill-posed. Traditional methods usually employ interaction to deal with the image matting problem with trimaps and strokes, and cannot run on the mobile phone in real-time. In this paper, we propose a real-time automatic deep matting approach for mobile devices. By leveraging the densely connected blocks and the dilated convolution, a light full convolutional network is designed to predict a coarse binary mask for portrait images. And a feathering block, which is edge-preser…
SynergyWarpNet: Attention-Guided Cooperative Warping for Neural Portrait Animation
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（人工智能联合实验室，人工智能研究院，上海交通大学）；Defense Innovation Institute, Academy of Military Science（国防创新研究院，军事科学院）；Intelligent Game and Decision Laboratory（智能游戏与决策实验室）
GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expression
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；NIO（蔚来）；Banma（斑马）；Beihang University（北京航空航天大学）
Mamba-Enhanced Implicit Motion Learning for Audio-Driven Portrait Animation
Fujian Provincial Natural Science Foundation of China（福建省自然科学基金委员会）；Giant Interactive Group Inc.（巨匠互动集团有限公司）；National Natural Science Foundation of China（国家自然科学基金委员会）
Millions of images of human faces are captured every single day; but these photographs portray the likeness of an individual with a fixed pose, expression, and appearance. Portrait image animation enables the post-capture adjustment of these attributes from a single image while maintaining a photorealistic reconstruction of the subject's likeness or identity. Still, current methods for portrait image animation are typically based on 2D warping operations or manipulations of a 2D generative adversarial network (GAN) and lack explicit mechanisms to enforce multi-view consistency. Thus these meth…
University of Trento（特伦托大学）；Zhejiang University（浙江大学）；Shandong University（山东大学）；ETH Zurich（苏黎世联邦理工学院）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；Illinois Institute of Technology（伊利诺伊理工学院）
This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze and high-resolution CelebH…
This paper presents a neural rendering method for controllable portrait video synthesis. Recent advances in volumetric neural rendering, such as neural radiance fields (NeRF), has enabled the photorealistic novel view synthesis of static scenes with impressive results. However, modeling dynamic and controllable objects as part of a scene with such scene representations is still challenging. In this work, we design a system that enables both novel view synthesis for portrait video, including the human subject and the scene background, and explicit control of the facial expressions through a low…
To the best of our knowledge, we first present a live system that generates personalized photorealistic talking-head animation only driven by audio signals at over 30 fps. Our system contains three stages. The first stage is a deep neural network that extracts deep audio features along with a manifold projection to project the features to the target person's speech space. In the second stage, we learn facial dynamics and motions from the projected audio features. The predicted motions include head poses and upper body motions, where the former is generated by an autoregressive probabilistic mo…
