10 papers
GIFT: Geometry-Invariant Fine-Tuning for Non-Lambertian Monocular Depth Estimation
Xianghui Fan, Zhaoyu Chen, Bingqian Wu +6
Monocular depth foundation models, benefiting from large-scale synthetic training data, have demonstrated strong generalization. However, they often hallucinate depth on non-Lamber…
Teleopit: A Full-Embodiment Humanoid Teleoperation System
Bingqian Wu, Zicheng Xu, Xianghui Fan +2
Humanoid teleoperation for demonstration collection requires coordinated whole-body motion, continuous dexterous hand control, and viewpoint control. Existing systems either simpli…
fMRI2Face: A Full-HD fMRI-Video Dataset and Geometry-Guided Neural Decoding Framework for Dynamic Human Face Reconstruction
Jingyang Huo, Xiangru Huang, Chentao Shen +6
Reconstructing dynamic human faces from brain activity provides a powerful way to study how the mind perceives identity, expression, and facial motion. However, progress in fMRI-ba…
KeyframeFace: Language-Driven Facial Animation via Semantic Keyframes
Jingchao Wu, Zejian Kang, Haibo Liu +2
Facial animation is a core component for creating digital characters in Computer Graphics (CG) industry. A typical production workflow relies on sparse, semantically meaningful key…
AudioFace: Language-Assisted Speech-Driven Facial Animation with Multimodal Language Models
Kai Zheng, Zejian Kang, Rui Mao +4
Speech-driven facial animation requires accurate correspondence between acoustic signals and facial motion, especially for articulation-related mouth movements. However, directly m…
SuperFace: Preference-Aligned Facial Expression Estimation Beyond Pseudo Supervision
Zejian Kang, Xuanyang Xu, Wentao Yang +6
Accurate facial estimation is crucial for realistic digital human animation, and ARKit blendshape coefficients offer an interpretable representation by mapping facial motions to se…