| 1 |
Asset-Driven Sematic Reconstruction of Dynamic Scene with Multi-Human-Object Interactions |
提出基于资产驱动的动态场景语义重建方法，解决多人-多物交互下的三维重建难题 |
3D gaussian splatting gaussian splatting human-object interaction |
|
|
| 2 |
Cross-Temporal 3D Gaussian Splatting for Sparse-View Guided Scene Update |
提出Cross-Temporal 3DGS，利用稀疏视图实现跨时序场景更新与重建 |
3D gaussian splatting 3DGS gaussian splatting |
|
|
| 3 |
SplatFont3D: Structure-Aware Text-to-3D Artistic Font Generation with Part-Level Style Control |
提出SplatFont3D框架，实现结构感知和部件级风格控制的3D艺术字体生成。 |
3D gaussian splatting gaussian splatting NeRF |
|
|
| 4 |
Odometry Without Correspondence from Inertially Constrained Ruled Surfaces |
提出一种基于惯性约束ruled surface的无对应点视觉里程计方法 |
visual odometry optical flow |
|
|
| 5 |
Describe Anything Anywhere At Any Moment |
提出DAAAM框架，实现大规模场景下任意时空位置的实时语义描述与推理。 |
scene understanding |
|
|
| 6 |
CC-FMO: Camera-Conditioned Zero-Shot Single Image to 3D Scene Generation with Foundation Model Orchestration |
CC-FMO：利用基础模型编排，实现相机条件下的单图零样本3D场景生成 |
pose estimation |
|
|
| 7 |
What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards |
提出NewtonRewards，通过可验证奖励后训练视频生成模型，提升物理真实性。 |
optical flow |
|
|