2 papers
cs.CV2026
GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors
Jiazheng Liu, Hang Li, Jiawei Zhang +5
Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos, but are severely constrained by hi…
cs.CV2026
Learning Gaussian Structure: Intervention-Guided Density Control for Feed-Forward Driving Reconstruction
Hang Li, Jiahe Li, Meiying Gu +3
Feed-forward Gaussian reconstruction has recently emerged as an efficient approach for driving scene reconstruction. However, prevailing LiDAR-based methods preserve the initial co…