Closed-Loop World Model Couples Driving Behavior and Visual Rendering
Researchers present a closed-loop interactive world model for autonomous driving that couples multi-agent behavior modeling with image-based rendering. Background-vehicle policies are fine-tuned with multi-agent reinforcement learning against an end-to-end ego planner that reacts to rendered images. A per-Gaussian diagnosis procedure attenuates view-dependent colors on under-observed Gaussians and fills never-observed surfaces, while signal lights are rendered from learned vehicle intentions. The paper reports an 85% reduction in divergence from real-world interaction behaviors and a 2.0 dB novel-view vehicle PSNR improvement over a state-of-the-art world model on long-tail closed-loop scenarios.
It offers a concrete method for making simulated driving interactions behaviorally and visually realistic, which matters for training and evaluating autonomous systems in unseen scenarios.
Comments & Questions (0)
No comments yet
Be the first to comment!