An official website of the United States government
In this paper, the authors explore different approaches to animating 3D facial emotions, some of which use manual keyframe animation and some of which use machine learning. To compare approaches the authors conducted an experiment consisting of side-by-side comparisons of animation clips generated by skeleton, blendshape, audio-driven, and vision-based capture facial animation techniques. Ninety-five participants viewed twenty face animation clips of characters expressing five distinct emotions (anger, sadness, happiness, fear, neutral), which were created using the four different facial animation techniques. After viewing each clip, the participants were asked to identify the emotions that the characters appeared to be conveying and rate their naturalness. Findings showed that the naturalness ratings of the happy emotion produced by the four methods tended to be consistent, whereas the naturalness ratings of the fear emotion created with skeletal animation were significantly higher than the other methods. Recognition of sad and neutral emotions were very low for all methods as compared to the other emotions. Overall, the skeleton approach had significantly higher ratings for naturalness and higher recognition rate than the other methods.
more »
« less
Disentangling audio content and emotion with adaptive instance normalization for expressive facial animation synthesis
Abstract 3D facial animation synthesis from audio has been a focus in recent years. However, most existing literature works are designed to map audio and visual content, providing limited knowledge regarding the relationship between emotion in audio and expressive facial animation. This work generates audio‐matching facial animations with the specified emotion label. In such a task, we argue that separating the content from audio is indispensable—the proposed model must learn to generate facial content from audio content while expressions from the specified emotion. We achieve it by an adaptive instance normalization module that isolates the content in the audio and combines the emotion embedding from the specified label. The joint content‐emotion embedding is then used to generate 3D facial vertices and texture maps. We compare our method with state‐of‐the‐art baselines, including the facial segmentation‐based and voice conversion‐based disentanglement approaches. We also conduct a user study to evaluate the performance of emotion conditioning. The results indicate that our proposed method outperforms the baselines in animation quality and expression categorization accuracy.
more »
« less
- PAR ID:
- 10375471
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Computer Animation and Virtual Worlds
- Volume:
- 33
- Issue:
- 3-4
- ISSN:
- 1546-4261
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Reconstructing 3D faces with facial geometry from single images has allowed for major advances in animation, generative models, and virtual reality. However, this ability to represent faces with their 3D features is not as fully explored by the facial expression inference (FEI) community. This study therefore aims to investigate the impacts of integrating such 3D representations into the FEI task, specifically for facial expression classification and face-based valence-arousal (VA) estimation. To accomplish this, we first assess the performance of two 3D face representations (both based on the 3D morphable model, FLAME) for the FEI tasks. We further explore two fusion architectures, intermediate fusion and late fusion, for integrating the 3D face representations with existing 2D inference frameworks. To evaluate our proposed architecture, we extract the corresponding 3D representations and perform extensive tests on the AffectNet and RAF-DB datasets. Our experimental results demonstrate that our proposed method outperforms the state-of-the-art AffectNet VA estimation and RAF-DB classification tasks. Moreover, our method can act as a complement to other existing methods to boost performance in many emotion inference tasks.more » « less
-
The emergence of photorealistic and cinematic non-player character (NPC) animation presents new challenges for video game developers. Game player expectations of cinematic acting styles bring a more sophisticated aesthetic in the representation of social interaction. New methods can streamline workflow by integrating actor-driven character design into the development of game character AI and animation. A workflow that tracks actor performance to final neural network (NN) design depends on a rigorous method of producing single-actor video corpora from which to train emotion AI NN models. While numerous video corpora have been developed to study emotion elicitation of the face from which to test theoretical models and train neural networks to recognize emotion, developing single-actor corpora to train NNs of NPCs in video games is uncommon. A class of facial emotion recognition (FER) products have enabled production of single-actor video corpora that use emotion analysis data. This paper introduces a single-actor game character corpora workflow for game character developers. The proposed method uses a single actor video corpus and dataset with the intent to train and implement a NN in an off-the-shelf video game engine for facial animation of an NPC. The efficacy of using a NN-driven animation controller has already been demonstrated (Schiffer, 2021, Kozasa et. al 2006). This paper focuses on using a single-actor video corpus for the purpose of training a NN-driven animation controller.more » « less
-
Online classes are typically conducted by using video conferencing software such as Zoom, Microsoft Teams, and Google Meet. Research has identified drawbacks of online learning, such as “Zoom fatigue”, characterized by distractions and lack of engagement. This study presents the CUNY Affective and Responsive Virtual Environment (CARVE) Hub, a novel virtual reality hub that uses a facial emotion classification model to generate emojis for affective and informal responsive interaction in a 3D virtual classroom setting. A web-based machine learning model is employed for facial emotion classification, enabling students to communicate four basic emotions live through automated web camera capture in a virtual classroom without activating their cameras. The experiment is conducted in undergraduate classes on both Zoom and CARVE, and the results of a survey indicate that students have a positive perception of interactions in the proposed virtual classroom compared with Zoom. Correlations between automated emojis and interactions are also observed. This study discusses potential explanations for the improved interactions, including a decrease in pressure on students when they are not showing faces. In addition, video panels in traditional remote classrooms may be useful for communication but not for interaction. Students favor features in virtual reality, such as spatial audio and the ability to move around, with collaboration being identified as the most helpful feature.more » « less
-
Speech emotion recognition (SER) is a challenging task due to the limited availability of real-world labeled datasets. Since it is easier to find unlabeled data, the use of self-supervised learning (SSL) has become an attractive alternative. This study proposes new pre-text tasks for SSL to improve SER. While our target application is SER, the proposed pre-text tasks include audio-visual formulations, leveraging the relationship between acoustic and facial features. Our proposed approach introduces three new unimodal and multimodal pre-text tasks that are carefully designed to learn better representations for predicting emotional cues from speech. Task 1 predicts energy variations (high or low) from a speech sequence. Task 2 uses speech features to predict facial activation (high or low) based on facial landmark movements. Task 3 performs a multi-class emotion recognition task on emotional labels obtained from combinations of action units (AUs) detected across a video sequence. We pre-train a network with 60.92 hours of unlabeled data, fine-tuning the model for the downstream SER task. The results on the CREMA-D dataset show that the model pre-trained on the proposed domain-specific pre-text tasks significantly improves the precision (up to 5.1%), recall (up to 4.5%), and F1-scores (up to 4.9%) of our SER system.more » « less
