Zhilei Liu

Sen Chen, Zhilei Liu, Jiaxing Liu et al.

Talking head generation is to synthesize a lip-synchronized talking head video by inputting an arbitrary face image and corresponding audio clips. Existing methods ignore not only the interaction and relationship of cross-modal information, but also the local driving information of the mouth muscles. In this study, we propose a novel generative framework that contains a dilated non-causal temporal convolutional self-attention network as a multimodal fusion module to promote the relationship learning of cross-modal features. In addition, our proposed method uses both audio- and speech-related facial action units (AUs) as driving information. Speech-related AU information can guide mouth movements more accurately. Because speech is highly correlated with speech-related AUs, we propose an audio-to-AU module to predict speech-related AU information. We utilize pre-trained AU classifier to ensure that the generated images contain correct AU information. We verify the effectiveness of the proposed model on the GRID and TCD-TIMIT datasets. An ablation study is also conducted to verify the contribution of each component. The results of quantitative and qualitative experiments demonstrate that our method outperforms existing methods in terms of both image quality and lip-sync accuracy.

Nanhan Shen, Zhilei Liu

Emotional Talking Face synthesis is pivotal in multimedia and signal processing, yet existing 3D methods suffer from two critical challenges: poor audio-vision emotion alignment, manifested as difficult audio emotion extraction and inadequate control over emotional micro-expressions; and a one-size-fits-all multi-view fusion strategy that overlooks uncertainty and feature quality differences, undermining rendering quality. We propose UA-3DTalk, Uncertainty-Aware 3D Emotional Talking Face Synthesis with emotion prior distillation, which has three core modules: the Prior Extraction module disentangles audio into content-synchronized features for alignment and person-specific complementary features for individualization; the Emotion Distillation module introduces a multi-modal attention-weighted fusion mechanism and 4D Gaussian encoding with multi-resolution code-books, enabling fine-grained audio emotion extraction and precise control of emotional micro-expressions; the Uncertainty-based Deformation deploys uncertainty blocks to estimate view-specific aleatoric (input noise) and epistemic (model parameters) uncertainty, realizing adaptive multi-view fusion and incorporating a multi-head decoder for Gaussian primitive optimization to mitigate the limitations of uniform-weight fusion. Extensive experiments on regular and emotional datasets show UA-3DTalk outperforms state-of-the-art methods like DEGSTalk and EDTalk by 5.2% in E-FID for emotion alignment, 3.1% in SyncC for lip synchronization, and 0.015 in LPIPS for rendering quality. Project page: https://mrask999.github.io/UA-3DTalk

Jiyuan Cao, Zhilei Liu, Yong Zhang

Facial Action Unit (AU) detection is a crucial task for emotion analysis from facial movements. The apparent differences of different subjects sometimes mislead changes brought by AUs, resulting in inaccurate results. However, most of the existing AU detection methods based on deep learning didn't consider the identity information of different subjects. The paper proposes a meta-learning-based cross-subject AU detection model to eliminate the identity-caused differences. Besides, a transformer-based relation learning module is introduced to learn the latent relations of multiple AUs. To be specific, our proposed work is composed of two sub-tasks. The first sub-task is meta-learning-based AU local region representation learning, called MARL, which learns discriminative representation of local AU regions that incorporates the shared information of multiple subjects and eliminates identity-caused differences. The second sub-task uses the local region representation of AU of the first sub-task as input, then adds relationship learning based on the transformer encoder architecture to capture AU relationships. The entire training process is cascaded. Ablation study and visualization show that our MARL can eliminate identity-caused differences, thus obtaining a robust and generalized AU discriminative embedding representation. Our results prove that on the two public datasets BP4D and DISFA, our method is superior to the state-of-the-art technology, and the F1 score is improved by 1.3% and 1.4%, respectively.

Chenggong Zhang, Zhilei Liu

The face super-resolution (FSR) task is to reconstruct high-resolution face images from low-resolution inputs. Recent works have achieved success on this task by utilizing facial priors such as facial landmarks. Most existing methods pay more attention to global shape and structure information, but less to local texture information, which makes them cannot recover local details well. In this paper, we propose a novel recurrent convolutional network based framework for face super-resolution, which progressively introduces both global shape and local texture information. We take full advantage of the intermediate outputs of the recurrent network, and landmarks information and facial action units (AUs) information are extracted in the output of the first and second steps respectively, rather than low-resolution input. Moreover, we introduced AU classification results as a novel quantitative metric for facial details restoration. Extensive experiments show that our proposed method significantly outperforms state-of-the-art FSR methods in terms of image quality and facial details restoration.

Juan Song, Zhilei Liu

Facial action unit (AU) detection is a challenging task due to the scarcity of manual annotations. Recent works on AU detection with self-supervised learning have emerged to address this problem, aiming to learn meaningful AU representations from numerous unlabeled data. However, most existing AU detection works with self-supervised learning utilize global facial features only, while AU-related properties such as locality and relevance are not fully explored. In this paper, we propose a novel self-supervised framework for AU detection with the region and relation learning. In particular, AU related attention map is utilized to guide the model to focus more on AU-specific regions to enhance the integrity of AU local features. Meanwhile, an improved Optimal Transport (OT) algorithm is introduced to exploit the correlation characteristics among AUs. In addition, Swin Transformer is exploited to model the long-distance dependencies within each AU region during feature learning. The evaluation results on BP4D and DISFA demonstrate that our proposed method is comparable or even superior to the state-of-the-art self-supervised learning methods and supervised AU detection methods.

Zhiwen Shao, Zhilei Liu, Jianfei Cai et al.

Facial action unit (AU) detection and face alignment are two highly correlated tasks, since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. However, most existing AU detection works handle the two tasks independently by treating face alignment as a preprocessing, and often use landmarks to predefine a fixed region or attention for each AU. In this paper, we propose a novel end-to-end deep learning framework for joint AU detection and face alignment, which has not been explored before. In particular, multi-scale shared feature is learned firstly, and high-level feature of face alignment is fed into AU detection. Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively. Finally, the assembled local features are integrated with face alignment feature and global feature for AU detection. Extensive experiments demonstrate that our framework (i) significantly outperforms the state-of-the-art AU detection methods on the challenging BP4D, DISFA, GFT and BP4D+ benchmarks, (ii) can adaptively capture the irregular region of each AU, (iii) achieves competitive performance for face alignment, and (iv) also works well under partial occlusions and non-frontal poses. The code for our method is available at https://github.com/ZhiwenShao/PyTorch-JAANet.

Chongke Bi, Xiaoxing Liu, Zhilei Liu

Talking face synthesis driven by audio is one of the current research hotspots in the fields of multidimensional signal processing and multimedia. Neural Radiance Field (NeRF) has recently been brought to this research field in order to enhance the realism and 3D effect of the generated faces. However, most existing NeRF-based methods either burden NeRF with complex learning tasks while lacking methods for supervised multimodal feature fusion, or cannot precisely map audio to the facial region related to speech movements. These reasons ultimately result in existing methods generating inaccurate lip shapes. This paper moves a portion of NeRF learning tasks ahead and proposes a talking face synthesis method via NeRF with attention-based disentanglement (NeRF-AD). In particular, an Attention-based Disentanglement module is introduced to disentangle the face into Audio-face and Identity-face using speech-related facial action unit (AU) information. To precisely regulate how audio affects the talking face, we only fuse the Audio-face with audio feature. In addition, AU information is also utilized to supervise the fusion of these two modalities. Extensive qualitative and quantitative experiments demonstrate that our NeRF-AD outperforms state-of-the-art methods in generating realistic talking face videos, including image quality and lip synchronization. To view video results, please refer to https://xiaoxingliu02.github.io/NeRF-AD.

Yuze Li, Zhilei Liu

Facial action unit (AU) detection remains challenging because it involves heterogeneous, AU-specific uncertainties arising at both the representation and decision stages. Recent methods have improved discriminative feature learning, but they often treat the AU representations as deterministic, overlooking uncertainty caused by visual noise, subject-dependent appearance variations, and ambiguous inter-AU relationships, all of which can substantially degrade robustness. Meanwhile, conventional point-estimation classifiers often provide poorly calibrated confidence, producing overconfident predictions, especially under the severe label imbalance typical of AU datasets. We propose UAU-Net, an Uncertainty-aware AU detection framework that explicitly models uncertainty at both stages. At the representation stage, we introduce CV-AFE, a conditional VAE (CVAE)-based AU feature extraction module that learns probabilistic AU representations by jointly estimating feature means and variances across multiple spatio-temporal scales; conditioning on AU labels further enables CV-AFE to capture uncertainty associated with inter-AU dependencies. At the decision stage, we design AB-ENN, an Asymmetric Beta Evidential Neural Network for multi-label AU detection, which parameterizes predictive uncertainty with Beta distributions and mitigates overconfidence via an asymmetric loss tailored to highly imbalanced binary labels. Extensive experiments on BP4D and DISFA show that UAU-Net achieves strong AU detection performance, and further analyses indicate that modeling uncertainty in both representation learning and evidential prediction improves robustness and reliability.

Xiaoxing Liu, Zhilei Liu, Chongke Bi

Talking head synthesis is to synthesize a lip-synchronized talking head video using audio. Recently, the capability of NeRF to enhance the realism and texture details of synthesized talking heads has attracted the attention of researchers. However, most current NeRF methods based on audio are exclusively concerned with the rendering of frontal faces. These methods are unable to generate clear talking heads in novel views. Another prevalent challenge in current 3D talking head synthesis is the difficulty in aligning acoustic and visual spaces, which often results in suboptimal lip-syncing of the generated talking heads. To address these issues, we propose Neural Radiance Field with 3D Prior Aided Audio Disentanglement for Talking Head Synthesis (NeRF-3DTalker). Specifically, the proposed method employs 3D prior information to synthesize clear talking heads with free views. Additionally, we propose a 3D Prior Aided Audio Disentanglement module, which is designed to disentangle the audio into two distinct categories: features related to 3D awarded speech movements and features related to speaking style. Moreover, to reposition the generated frames that are distant from the speaker's motion space in the real space, we have devised a local-global Standardized Space. This method normalizes the irregular positions in the generated frames from both global and local semantic perspectives. Through comprehensive qualitative and quantitative experiments, it has been demonstrated that our NeRF-3DTalker outperforms state-of-the-art in synthesizing realistic talking head videos, exhibiting superior image quality and lip synchronization. Project page: https://nerf-3dtalker.github.io/NeRF-3Dtalker.

Zhilei Liu, Chenggong Zhang

Traditional face super-resolution (FSR) methods trained on synthetic datasets usually have poor generalization ability for real-world face images. Recent work has utilized complex degradation models or training networks to simulate the real degradation process, but this limits the performance of these methods due to the domain differences that still exist between the generated low-resolution images and the real low-resolution images. Moreover, because of the existence of a domain gap, the semantic feature information of the target domain may be affected when synthetic data and real data are utilized to train super-resolution models simultaneously. In this study, a real-world face super-resolution teacher-student model is proposed, which considers the domain gap between real and synthetic data and progressively includes diverse edge information by using the recurrent network's intermediate outputs. Extensive experiments demonstrate that our proposed approach surpasses state-of-the-art methods in obtaining high-quality face images for real-world FSR.

Sen Chen, Zhilei Liu, Jiaxing Liu et al.

The task of talking head generation is to synthesize a lip synchronized talking head video by inputting an arbitrary face image and audio clips. Most existing methods ignore the local driving information of the mouth muscles. In this paper, we propose a novel recurrent generative network that uses both audio and speech-related facial action units (AUs) as the driving information. AU information related to the mouth can guide the movement of the mouth more accurately. Since speech is highly correlated with speech-related AUs, we propose an Audio-to-AU module in our system to predict the speech-related AU information from speech. In addition, we use AU classifier to ensure that the generated images contain correct AU information. Frame discriminator is also constructed for adversarial training to improve the realism of the generated face. We verify the effectiveness of our model on the GRID dataset and TCD-TIMIT dataset. We also conduct an ablation study to verify the contribution of each component in our model. Quantitative and qualitative experiments demonstrate that our method outperforms existing methods in both image quality and lip-sync accuracy.

Chenggong Zhang, Juan Song, Qingyang Zhang et al.

This paper describes an approach to the facial action unit (AU) detection. In this work, we present our submission to the Field Affective Behavior Analysis (ABAW) 2021 competition. The proposed method uses the pre-trained JAA model as the feature extractor, and extracts global features, face alignment features and AU local features on the basis of multi-scale features. We take the AU local features as the input of the graph convolution to further consider the correlation between AU, and finally use the fused features to classify AU. The detected accuracy was evaluated by 0.5*accuracy + 0.5*F1. Our model achieves 0.674 on the challenging Aff-Wild2 database.

Ruixin Xiao, Zhilei Liu, Baoyuan Wu

With the supervision from source domain only in class-level, existing unsupervised domain adaptation (UDA) methods mainly learn the domain-invariant representations from a shared feature extractor, which causes the source-bias problem. This paper proposes an unsupervised domain adaptation approach with Teacher-Student Competition (TSC). In particular, a student network is introduced to learn the target-specific feature space, and we design a novel competition mechanism to select more credible pseudo-labels for the training of student network. We introduce a teacher network with the structure of existing conventional UDA method, and both teacher and student networks compete to provide target pseudo-labels to constrain every target sample's training in student network. Extensive experiments demonstrate that our proposed TSC framework significantly outperforms the state-of-the-art domain adaptation methods on Office-31 and ImageCLEF-DA benchmarks.

Zhilei Liu, Yunpeng Wu, Le Li et al.

Previous research on face restoration often focused on repairing a specific type of low-quality facial images such as low-resolution (LR) or occluded facial images. However, in the real world, both the above-mentioned forms of image degradation often coexist. Therefore, it is important to design a model that can repair LR occluded images simultaneously. This paper proposes a multi-scale feature graph generative adversarial network (MFG-GAN) to implement the face restoration of images in which both degradation modes coexist, and also to repair images with a single type of degradation. Based on the GAN, the MFG-GAN integrates the graph convolution and feature pyramid network to restore occluded low-resolution face images to non-occluded high-resolution face images. The MFG-GAN uses a set of customized losses to ensure that high-quality images are generated. In addition, we designed the network in an end-to-end format. Experimental results on the public-domain CelebA and Helen databases show that the proposed approach outperforms state-of-the-art methods in performing face super-resolution (up to 4x or 8x) and face completion simultaneously. Cross-database testing also revealed that the proposed approach has good generalizability.

Yong Zhang, Le Li, Zhilei Liu et al.

Kinship face synthesis is an interesting topic raised to answer questions like "what will your future children look like?". Published approaches to this topic are limited. Most of the existing methods train models for one-versus-one kin relation, which only consider one parent face and one child face by directly using an auto-encoder without any explicit control over the resemblance of the synthesized face to the parent face. In this paper, we propose a novel method for controllable descendant face synthesis, which models two-versus-one kin relation between two parent faces and one child face. Our model consists of an inheritance module and an attribute enhancement module, where the former is designed for accurate control over the resemblance between the synthesized face and parent faces, and the latter is designed for control over age and gender. As there is no large scale database with father-mother-child kinship annotation, we propose an effective strategy to train the model without using the ground truth descendant faces. No carefully designed image pairs are required for learning except only age and gender labels of training faces. We conduct comprehensive experimental evaluations on three public benchmark databases, which demonstrates encouraging results.

Zhilei Liu, Le Li, Yunpeng Wu et al.

Facial expression analysis in the wild is challenging when the facial image is with low resolution or partial occlusion. Considering the correlations among different facial local regions under different facial expressions, this paper proposes a novel facial expression restoration method based on generative adversarial network by integrating an improved graph convolutional network (IGCN) and region relation modeling block (RRMB). Unlike conventional graph convolutional networks taking vectors as input features, IGCN can use tensors of face patches as inputs. It is better to retain the structure information of face patches. The proposed RRMB is designed to address facial generative tasks including inpainting and super-resolution with facial action units detection, which aims to restore facial expression as the ground-truth. Extensive experiments conducted on BP4D and DISFA benchmarks demonstrate the effectiveness of our proposed method through quantitative and qualitative evaluations.

Zhilei Liu, Jiahui Dong, Cuicui Zhang et al.

Most existing AU detection works considering AU relationships are relying on probabilistic graphical models with manually extracted features. This paper proposes an end-to-end deep learning framework for facial AU detection with graph convolutional network (GCN) for AU relation modeling, which has not been explored before. In particular, AU related regions are extracted firstly, latent representations full of AU information are learned through an auto-encoder. Moreover, each latent representation vector is feed into GCN as a node, the connection mode of GCN is determined based on the relationships of AUs. Finally, the assembled features updated through GCN are concatenated for AU detection. Extensive experiments on BP4D and DISFA benchmarks demonstrate that our framework significantly outperforms the state-of-the-art methods for facial AU detection. The proposed framework is also validated through a series of ablation studies.

Zhilei Liu, Diyi Liu, Yunpeng Wu

Facial expression synthesis or editing has recently received increasing attention in the field of affective computing and facial expression modeling. However, most existing facial expression synthesis works are limited in paired training data, low resolution, identity information damaging, and so on. To address those limitations, this paper introduces a novel Action Unit (AU) level facial expression synthesis method called Local Attentive Conditional Generative Adversarial Network (LAC-GAN) based on face action units annotations. Given desired AU labels, LAC-GAN utilizes local AU regional rules to control the status of each AU and attentive mechanism to combine several of them into the whole photo-realistic facial expressions or arbitrary facial expressions. In addition, unpaired training data is utilized in our proposed method to train the manipulation module with the corresponding AU labels, which learns a mapping between a facial expression manifold. Extensive qualitative and quantitative evaluations are conducted on the commonly used BP4D dataset to verify the effectiveness of our proposed AU synthesis method.

Zhiwen Shao, Zhilei Liu, Jianfei Cai et al.

Attention mechanism has recently attracted increasing attentions in the field of facial action unit (AU) detection. By finding the region of interest of each AU with the attention mechanism, AU-related local features can be captured. Most of the existing attention based AU detection works use prior knowledge to predefine fixed attentions or refine the predefined attentions within a small range, which limits their capacity to model various AUs. In this paper, we propose an end-to-end deep learning based attention and relation learning framework for AU detection with only AU labels, which has not been explored before. In particular, multi-scale features shared by each AU are learned firstly, and then both channel-wise and spatial attentions are adaptively learned to select and extract AU-related local features. Moreover, pixel-level relations for AUs are further captured to refine spatial attentions so as to extract more relevant local features. Without changing the network architecture, our framework can be easily extended for AU intensity estimation. Extensive experiments show that our framework (i) soundly outperforms the state-of-the-art methods for both AU detection and AU intensity estimation on the challenging BP4D, DISFA, FERA 2015 and BP4D+ benchmarks, (ii) can adaptively capture the correlated regions of each AU, and (iii) also works well under severe occlusions and large poses.

Haotian Guan, Zhilei Liu, Longbiao Wang et al.

Recently, increasing attention has been directed to the study of the speech emotion recognition, in which global acoustic features of an utterance are mostly used to eliminate the content differences. However, the expression of speech emotion is a dynamic process, which is reflected through dynamic durations, energies, and some other prosodic information when one speaks. In this paper, a novel local dynamic pitch probability distribution feature, which is obtained by drawing the histogram, is proposed to improve the accuracy of speech emotion recognition. Compared with most of the previous works using global features, the proposed method takes advantage of the local dynamic information conveyed by the emotional speech. Several experiments on Berlin Database of Emotional Speech are conducted to verify the effectiveness of the proposed method. The experimental results demonstrate that the local dynamic information obtained with the proposed method is more effective for speech emotion recognition than the traditional global features.

Zhiwen Shao, Zhilei Liu, Jianfei Cai et al.

Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. Most existing AU detection works often treat face alignment as a preprocessing and handle the two tasks independently. In this paper, we propose a novel end-to-end deep learning framework for joint AU detection and face alignment, which has not been explored before. In particular, multi-scale shared features are learned firstly, and high-level features of face alignment are fed into AU detection. Moreover, to extract precise local features, we propose an adaptive attention learning module to refine the attention map of each AU adaptively. Finally, the assembled local features are integrated with face alignment features and global features for AU detection. Experiments on BP4D and DISFA benchmarks demonstrate that our framework significantly outperforms the state-of-the-art methods for AU detection.

Zhilei Liu, Guoxian Song, Jianfei Cai et al.

Employing deep learning-based approaches for fine-grained facial expression analysis, such as those involving the estimation of Action Unit (AU) intensities, is difficult due to the lack of a large-scale dataset of real faces with sufficiently diverse AU labels for training. In this paper, we consider how AU-level facial image synthesis can be used to substantially augment such a dataset. We propose an AU synthesis framework that combines the well-known 3D Morphable Model (3DMM), which intrinsically disentangles expression parameters from other face attributes, with models that adversarially generate 3DMM expression parameters conditioned on given target AU labels, in contrast to the more conventional approach of generating facial images directly. In this way, we are able to synthesize new combinations of expression parameters and facial images from desired AU labels. Extensive quantitative and qualitative results on the benchmark DISFA dataset demonstrate the effectiveness of our method on 3DMM facial expression parameter synthesis and data augmentation for deep learning-based AU intensity estimation.

Yan Ji, Licheng Liu, Hongcui Wang et al.

The 2010 Silent Speech Challenge benchmark is updated with new results obtained in a Deep Learning strategy, using the same input features and decoding strategy as in the original article. A Word Error Rate of 6.4% is obtained, compared to the published value of 17.4%. Additional results comparing new auto-encoder-based features with the original features at reduced dimensionality, as well as decoding scenarios on two different language models, are also presented. The Silent Speech Challenge archive has been updated to contain both the original and the new auto-encoder features, in addition to the original raw data.