4 papers
Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated Mesh
Junhao Chen, Mingjin Chen, Henghaofan Zhang +10
Pretrained video diffusion models can act as renderers when the desired scene state is already specified by an animated mesh, a camera trajectory, and a reference image. This 4D ge…
PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation
Junhao Chen, Xiang Li, Mingjin Chen +9
Code is the medium through which large language models generate structured artifacts: charts, scientific figures, vector graphics, CAD models, 3D scenes, and hardware designs are a…
One Video, One World: Turning Monocular Video into Physical 4D Scenes
Junhao Chen, Boran Zhang, Mingjin Chen +7
We introduce \textbf{OVOW}, the first training-free system that reconstructs \emph{instance-level, simulation-ready} 4D mesh scenes from a single monocular video. Recent 4D reconst…
Delving into Mapping Uncertainty for Mapless Trajectory Prediction
Zongzheng Zhang, Xuchong Qiu, Boran Zhang +11
Recent advances in autonomous driving are moving towards mapless approaches, where High-Definition (HD) maps are generated online directly from sensor data, reducing the need for e…