14 papers
ReconPhys: Reconstruct Appearance and Physical Attributes from Single Video
Boyuan Wang, Xiaofeng Wang, Yongkang Li +9
Reconstructing non-rigid objects with physical plausibility remains a significant challenge. Existing approaches leverage differentiable rendering for per-scene optimization, recov…
UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving
Guosheng Zhao, Yaozeng Wang, Xiaofeng Wang +10
World models have demonstrated significant promise for data synthesis in autonomous driving. However, existing methods predominantly concentrate on single-modality generation, typi…
Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding
Runqi Ouyang, Haoyun Li, Zhenyuan Zhang +6
Text-to-Motion generation has become a fundamental task in human-machine interaction, enabling the synthesis of realistic human motions from natural language descriptions. Although…
HumanDreamer-X: Photorealistic Single-image Human Avatars Reconstruction via Gaussian Restoration
Boyuan Wang, Runqi Ouyang, Xiaofeng Wang +8
Single-image human reconstruction is vital for digital human modeling applications but remains an extremely challenging task. Current approaches rely on generative models to synthe…
Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization
Yifan Chang, Jie Qin, Limeng Qiao +4
Vector quantization (VQ) is a key component in discrete tokenizers for image generation, but its training is often unstable due to straight-through estimation bias, one-step-behind…
DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding
Xiaoyi Bao, Chenwei Xie, Hao Tang +4
In recent years, the introduction of Multi-modal Large Language Models (MLLMs) into video understanding tasks has become increasingly prevalent. However, how to effectively integra…