5 papers
OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators
Hongyu Liu, Chun Wang, Feng Gao +6
We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce…
UIKA: Fast Universal Head Avatar from Pose-Free Images
Zijian Wu, Boyao Zhou, Liangxiao Hu +6
We present UIKA, a feed-forward animatable Gaussian head model from an arbitrary number of pose-free inputs, including a single image, multi-view captures, and smartphone-captured…
AvatarPointillist: AutoRegressive 4D Gaussian Avatarization
Hongyu Liu, Xuan Wang, Zijian Wu +7
We introduce AvatarPointillist, a novel framework for generating dynamic 4D Gaussian avatars from a single portrait image. At the core of our method is a decoder-only Transformer t…
LACON: Training Text-to-Image Model from Uncurated Data
Zhiyang Liang, Ziyu Wan, Hongyu Liu +4
The success of modern text-to-image generation is largely attributed to massive, high-quality datasets. Currently, these datasets are curated through a filter-first paradigm that a…
HeadLighter: Disentangling Illumination in Generative 3D Gaussian Heads via Lightstage Captures
Yating Wang, Yuan Sun, Xuan Wang +6
Recent 3D-aware head generative models based on 3D Gaussian Splatting achieve real-time, photorealistic and view-consistent head synthesis. However, a fundamental limitation persis…