Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation
Evaluating end-to-end autonomous driving (E2E-AD) remains challenging, as existing driving simulation methods often trade off closed-loop interactivity (e.g., CARLA) and real-world visual fidelity (e.g., nuScenes). We present \textbf{\emph{Point as Skeleton}}, a generative sensor simulation framework for state-updated autoregressive driving video generation, in which an autoregressive generator synthesizes visual observations from step-wise updated ego states, actor states, scene maps, and point-cloud skeleton conditions. To support closed-loop rollout, we introduce Reset-and-Roll, which adapt
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
- Linked via arxiv authorSongbur Wong →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorXiaosong Jia →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorJunqi You →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorBo Zhang →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorPei Xu →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorRenqiu Xia →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorYuping Qiu →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorShaofeng Zhang →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorZelin Zhao →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorXuechao Yan →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorYuchen Zhou →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorYurui Chen →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorYiwen Guo →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorHang Xu →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat
- Linked via arxiv authorJunchi Yan →
Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulat