8 papers
Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining
Junxuan Li, Rawal Khirodkar, Chengan He +37
High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans wit…
LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D
Lingteng Qiu, Peihao Li, Heyuan Li +9
Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view…
DuoMo: Dual Motion Diffusion for World-Space Human Reconstruction
Yufu Wang, Evonne Ng, Soyong Shin +8
We present DuoMo, a generative method that recovers human motion in world-space coordinates from unconstrained videos with noisy or incomplete observations. Reconstructing such mot…
PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image
Peng Li, Yisheng He, Yingdong Hu +7
We present a feed-forward framework for Gaussian full-head synthesis from a single unposed image. Unlike previous work that relies on time-consuming GAN inversion and test-time opt…
Atlas Gaussians Diffusion for 3D Generation
Haitao Yang, Yuan Dong, Hanwen Jiang +3
Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidel…
LAM: Large Avatar Model for One-shot Animatable Gaussian Head
Yisheng He, Xiaodong Gu, Xiaodan Ye +6
We present LAM, an innovative Large Avatar Model for animatable Gaussian head reconstruction from a single image. Unlike previous methods that require extensive training on capture…