8 papers
SparseLGS: Sparse View Language Embedded Gaussian Splatting
Jun Hu, Zhang Chen, Zhong Li +2
Recently, several studies have combined Gaussian Splatting to obtain scene representations with language embeddings for open-vocabulary 3D scene understanding. While these methods…
LaGen: Towards Autoregressive LiDAR Scene Generation
Sizhuo Zhou, Xiaosong Jia, Fanrui Zhang +7
Generative world models for autonomous driving (AD) are of great value in applications such as data augmentation, closed-loop simulation, and safety-critical scenario evaluation. U…
ExpPortrait: Expressive Portrait Generation via Personalized Representation
Junyi Wang, Yudong Guo, Boyang Guo +2
While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challeng…
Controlling Avatar Diffusion with Learnable Gaussian Embedding
Xuan Gao, Jingtao Zhou, Dongyu Liu +2
Recent advances in diffusion models have made significant progress in digital human generation. However, most existing models still struggle to maintain 3D consistency, temporal co…
Hybrid Explicit Representation for Ultra-Realistic Head Avatars
Hongrui Cai, Yuting Xiao, Xuan Wang +5
We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time (>30fps at resolution). First, we propose a hybrid explici…
One Shot, One Talk: Whole-body Talking Avatar from a Single Image
Jun Xiang, Yudong Guo, Leipeng Hu +3
Building realistic and animatable avatars still requires minutes of multi-view or monocular self-rotating videos, and most methods lack precise control over gestures and expression…