Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
3DCarGen: Scalable 3D Car Generation via 3D-consistent Multi-view Synthesis
Hongli Xiao, Youjian Zhang, Yaohui Jin +3
High-quality 3D vehicle assets are essential for autonomous driving simulation. Although multi-view diffusion-based paradigms enable controllable single-image reconstruction, they…
cs.CV2025
PASG: A Closed-Loop Framework for Automated Geometric Primitive Extraction and Semantic Anchoring in Robotic Manipulation
Zhihao Zhu, Yifan Zheng, Siyu Pan +2
The fragmentation between high-level task semantics and low-level geometric features remains a persistent challenge in robotic manipulation. While vision-language models (VLMs) hav…