6 papers
Future Rendering Future Surface: A Benchmark and Dataset for Dynamic Surface Reconstruction Beyond the Observed Window
Yukun Shi, Minglun Gong
Dynamic-scene reconstruction is almost always evaluated inside the observed time window, yet deployment settings such as AR overlays, robot interaction, and anticipatory planning n…
Skeletal-Anchored Dual Harmonics for Structured 3D Modeling
Zhentao Huang, Changhao Li, Ruizhen Hu +2
We present Skeletal-Anchored Dual Harmonics (SADH), a novel 3D shape representation that tightly couples local surface geometry with internal meso-skeletal organization. SADH repre…
CineAGI: Character-Consistent Movie Creation through LLM-Orchestrated Multi-Modal Generation and Cross-Scene Integration
Tianyidan Xie, Zhentao Huang, Mingjie Wang +4
Automated movie creation requires coordinating multiple characters, modalities, and narrative elements across extended sequences -- a challenge that existing end-to-end approaches…
PhysLayer: Language-Guided Layered Animation with Depth-Aware Physics
Tianyidan Xie, Zhentao Huang, Mingjie Wang +4
Existing image-to-video generation methods often produce physically implausible motions and lack precise control over object dynamics. While prior approaches have incorporated phys…
Gaussian Set Surface Reconstruction through Per-Gaussian Optimization
Zhentao Huang, Di Wu, Zhenbang He +1
3D Gaussian Splatting (3DGS) effectively synthesizes novel views through its flexible representation, yet fails to accurately reconstruct scene geometry. While modern variants like…
Textured-GS: Gaussian Splatting with Spatially Defined Color and Opacity
Zhentao Huang, Minglun Gong
In this paper, we introduce Textured-GS, an innovative method for rendering Gaussian splatting that incorporates spatially defined color and opacity variations using Spherical Harm…