English
Related papers

Related papers: Allo-AVA: A Large-Scale Multimodal Conversational …

200 papers

We introduce Nymeria - a large-scale, diverse, richly annotated human motion dataset collected in the wild with multiple multimodal egocentric devices. The dataset comes with a) full-body ground-truth motion; b) multiple multimodal…

Due to the increasing demand in films and games, synthesizing 3D avatar animation has attracted much attention recently. In this work, we present a production-ready text/speech-driven full-body animation synthesis system. Given the text and…

Graphics · Computer Science 2022-06-01 Wenlin Zhuang , Jinwei Qi , Peng Zhang , Bang Zhang , Ping Tan

In this work, we present TalkCuts, a large-scale dataset designed to facilitate the study of multi-shot human speech video generation. Unlike existing datasets that focus on single-shot, static viewpoints, TalkCuts offers 164k clips…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Jiaben Chen , Zixin Wang , Ailing Zeng , Yang Fu , Xueyang Yu , Siyuan Cen , Julian Tanke , Yihang Chen , Koichi Saito , Yuki Mitsufuji , Chuang Gan

Rendering photorealistic and dynamically moving human heads is crucial for ensuring a pleasant and immersive experience in AR/VR and video conferencing applications. However, existing methods often struggle to model challenging facial…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Cong Wang , Di Kang , Yan-Pei Cao , Linchao Bao , Ying Shan , Song-Hai Zhang

This work presents Interactive Conversational 3D Virtual Human (ICo3D), a method for generating an interactive, conversational, and photorealistic 3D human avatar. Based on multi-view captures of a subject, we create an animatable 3D face…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Richard Shaw , Youngkyoon Jang , Athanasios Papaioannou , Arthur Moreau , Helisa Dhamo , Zhensong Zhang , Eduardo Pérez-Pellitero

Human children far exceed modern machine learning algorithms in their sample efficiency, achieving high performance in key domains with much less data than current models. This ''data gap'' is a key challenge both for building intelligent…

Efficiently estimating the full-body pose with minimal wearable devices presents a worthwhile research direction. Despite significant advancements in this field, most current research neglects to explore full-body avatar estimation under…

Human-Computer Interaction · Computer Science 2024-07-03 Bo Qian , Zhenhuan Wei , Jiashuo Li , Xing Wei

Long context egocentric video understanding has recently attracted significant research attention, with augmented reality (AR) highlighted as one of its most important application domains. Nevertheless, the task remains highly challenging…

Machine Learning · Computer Science 2026-04-10 Qiance Tang , Ziqi Wang , Jieyu Lin , Ziyun Li , Barbara De Salvo , Sai Qian Zhang

With the recent advancements in AI, Intelligent Virtual Assistants (IVA) have become a ubiquitous part of every home. Going forward, we are witnessing a confluence of vision, speech and dialog system technologies that are enabling the IVAs…

Computation and Language · Computer Science 2018-12-21 Shachi H Kumar , Eda Okur , Saurav Sahay , Juan Jose Alvarado Leanos , Jonathan Huang , Lama Nachman

Existing video avatar models have demonstrated impressive capabilities in scenarios such as talking, public speaking, and singing. However, the majority of these methods exhibit limited alignment with respect to text instructions,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-01 Ruikui Wang , Jinheng Feng , Lang Tian , Huaishao Luo , Chaochao Li , Liangbo Zhou , Huan Zhang , Youzheng Wu , Xiaodong He

3D facial animation has attracted considerable attention due to its extensive applications in the multimedia field. Audio-driven 3D facial animation has been widely explored with promising results. However, multi-modal 3D facial animation,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-11 Sijing Wu , Yunhao Li , Yichao Yan , Huiyu Duan , Ziwei Liu , Guangtao Zhai

This paper proposes a novel direct Audio-Visual Speech to Audio-Visual Speech Translation (AV2AV) framework, where the input and output of the system are multimodal (i.e., audio and visual speech). With the proposed AV2AV, two key…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Jeongsoo Choi , Se Jin Park , Minsu Kim , Yong Man Ro

Realistic 3D full-body talking avatars hold great potential in AR, with applications ranging from e-commerce live streaming to holographic communication. Despite advances in 3D Gaussian Splatting (3DGS) for lifelike avatar creation,…

Computer Vision and Pattern Recognition · Computer Science 2025-07-24 Jianchuan Chen , Jingchuan Hu , Gaige Wang , Zhonghua Jiang , Tiansong Zhou , Zhiwen Chen , Chengfei Lv

This paper presents a novel approach for pretraining robotic manipulation Vision-Language-Action (VLA) models using a large corpus of unscripted real-life video recordings of human hand activities. Treating human hand as dexterous robot…

Faithful real-time facial animation is essential for avatar-mediated telepresence in Virtual Reality (VR). To emulate authentic communication, avatar animation needs to be efficient and accurate: able to capture both extreme and subtle…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Shaojie Bai , Te-Li Wang , Chenghui Li , Akshay Venkatesh , Tomas Simon , Chen Cao , Gabriel Schwartz , Ryan Wrench , Jason Saragih , Yaser Sheikh , Shih-En Wei

Full-body avatars are suggested to be beneficial for communication in virtual environments, and consistency between users' voices and gestures is considered essential to ensure communication quality. This paper propose extending the…

Human-Computer Interaction · Computer Science 2023-09-27 Yong-Hao Hu , Kenichiro Ito , Ayumi Igarashi

This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination. Variability allows the avatar to exhibit a wide range of motions even with similar…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Yifei Liu , Qiong Cao , Yandong Wen , Huaiguang Jiang , Changxing Ding

Animatable head avatar generation typically requires extensive data for training. To reduce the data requirements, a natural solution is to leverage existing data-free static avatar generation methods, such as pre-trained diffusion models…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Zhenglin Zhou , Fan Ma , Hehe Fan , Tat-Seng Chua

Since the beginning of the COVID-19 pandemic, remote conferencing and school-teaching have become important tools. The previous applications aim to save the commuting cost with real-time interactions. However, our application is going to…

Artificial Intelligence · Computer Science 2022-10-14 Aolan Sun , Xulong Zhang , Tiandong Ling , Jianzong Wang , Ning Cheng , Jing Xiao

Despite progress in human motion capture, existing multi-view methods often face challenges in estimating the 3D pose and shape of multiple closely interacting people. This difficulty arises from reliance on accurate 2D joint estimations,…

Computer Vision and Pattern Recognition · Computer Science 2024-08-21 Feichi Lu , Zijian Dong , Jie Song , Otmar Hilliges
‹ Prev 1 3 4 5 6 7 10 Next ›