4 papers
LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation
Tianbao Zhang, Zeyu Liu, Shuyu Wu +4
Real-time 3D perception is crucial for robotics, augmented reality, and embodied intelligence applications. Existing multi-view stereo (MVS) methods primarily rely on geometric cor…
2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction
Tianbao Zhang, Zhenyu Liang, Zhenbo Song +7
High-resolution geometric prediction is essential for robust perception in autonomous driving, robotics, and AR/MR, but current foundation models are fundamentally limited by their…
AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
Tianbao Zhang, Jian Zhao, Yuer Li +5
Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans and enhancing the capabilities of interactive virtual agents,…
Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstruction
Xudong Cai, Shuo Wang, Peng Wang +7
Reconstructing dense geometry for dynamic scenes from a monocular video is a critical yet challenging task. Recent memory-based methods enable efficient online reconstruction, but…