AIConfPaper
← Search

Xuangeng Chu

9 accepted papers

2026

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

Yichen Peng, Jyun-Ting Song, Siyeol Jung, Ulsan National Institute of Science & Technology blank, Ruofan Liu, Haiyang Liu +5
CVPR 2026

Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a single audio stream to a single speaker's motion, without considering social context or modeling the mutual dynamics between

Cited by 0Source ↗Scholar ↗
2026

UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking

Xuangeng Chu, Ruicong Liu, Yifei Huang, Yun Liu, Yichen Peng, Bo Zheng
CVPR 2026

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening.However, modeling the listener is exceptionally challenging: direct audio-driven training fails, producing stiff, static listening motions. This

Cited by 0Source ↗code ↗Scholar ↗
2025

I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions

Shuhong Liu, Lin Gu, Ziteng Cui, Xuangeng Chu, Tatsuya Harada
NeurIPS 2025poster

Participating in efforts to endow generative AI with the 3D physical world perception, we propose I2-NeRF, a novel neural radiance field framework that enhances isometric and isotropic metric perception under media degradation. While existing NeRF models predominantly rely on object-centric sampling…

Cited by 0Source ↗Scholar ↗
2025

Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding

Ryo Umagami, Liu Yue, Xuangeng Chu, Ryuto Fukushima, Tetsuya Narita, Yusuke Mukuta +3
NeurIPS 2025poster

Human motion is inherently intentional, yet most motion modeling paradigms focus on low-level kinematics, overlooking the semantic and causal factors that drive behavior. Existing datasets further limit progress: they capture short, decontextualized actions in static scenes, providing little groundi…

Cited by 0Source ↗Scholar ↗
2025

Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment

Ziteng Cui, Xuangeng Chu, Tatsuya Harada
CVPR 2025poster

Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality. This challenge becomes more pronounced in multi-view scenarios, where vari…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

Xuangeng Chu, Yu Li, Ailing Zeng, Tianyu Yang, Lijian Lin, Yunfei Liu +1
ICLR 2024poster

Head avatar reconstruction, crucial for applications in virtual reality, online meetings, gaming, and film industries, has garnered substantial attention within the computer vision community. The fundamental objective of this field is to faithfully recreate the head avatar and precisely control expr…

Cited by 26Source ↗PDF ↗code ↗Scholar ↗
2023

Accurate 3D Face Reconstruction with Facial Component Tokens

Tianke Zhang, Xuangeng Chu, Yunfei Liu, Lijian Lin, Zhendong Yang, Zhengzhuo Xu +5
ICCV 2023poster

Accurately reconstructing 3D faces from monocular images and videos is crucial for various applications, such as digital avatar creation. However, the current deep learning-based methods face significant challenges in achieving accurate reconstruction with disentangled facial parameters and ensuring…

Cited by 23PDF ↗Scholar ↗