EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents
cs.CV
Submitted: 2026-04-19
Updated: 2026-10-12
Comments: ECCV 2026, 26 pages
Journal ref: Computer Vision - ECCV 2026, LNCS 17034, pp. 444-461, Springer, 2026
DOI: 10.1007/978-3-032-37450-9_24
Project page: https://03skyboy.github.io/EmbodiedHead
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Layer Normalization
- Towards Seamless Interaction: Causal Turn-Level Modeling of Interactive 3D Conversational Head Dynamics
- PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
- TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis
- UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
- Affective Faces for Goal-Driven Dyadic Communication
- GLDiTalker: Speech-Driven 3D Facial Animation with Graph Latent Diffusion Transformer
- Flow Matching for Generative Modeling
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Decoupled Weight Decay Regularization
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
- GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- DiffPoseTalk: Speech-Driven Stylistic 3D Facial Animation and Head Pose Generation via Diffusion Models
- MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models