7 papers
Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation
Zhe Li, Honghao Qiao, Zhixin Xu +3
RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, g…
3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training
Jiaxin Shi, Xidong Zhang, Fucai Zhu +3
We propose a 3D-thinking-guided co-training framework that enables vision-language-action (VLA) models to perform 3D spatial reasoning implicitly during action prediction. Our core…
OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
Zhe Li, Weihao Yuan, Weichao Shen +3
Whole-body multi-modal human motion generation poses two primary challenges: creating an effective motion generation mechanism and integrating various modalities, such as text, spe…
MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow
Zhe Li, Yisheng He, Lei Zhong +6
Generating motion sequences conforming to a target style while adhering to the given content prompts requires accommodating both the content and style. In existing methods, the inf…
LaMP: Language-Motion Pretraining for Motion Generation, Retrieval, and Captioning
Zhe Li, Weihao Yuan, Yisheng He +7
Language plays a vital role in the realm of human motion. Existing methods have largely depended on CLIP text embeddings for motion generation, yet they fall short in effectively a…
MCMat: Multiview-Consistent and Physically Accurate PBR Material Generation
Shenhao Zhu, Lingteng Qiu, Xiaodong Gu +11
Existing 2D methods utilize UNet-based diffusion models to generate multi-view physically-based rendering (PBR) maps but struggle with multi-view inconsistency, while some 3D metho…