CARLA-GS is a modular pipeline that uses an LLM for semantic trajectory planning, CARLA for physics execution, and 3D Gaussian Splatting for photorealistic rendering to synthesize autonomous driving corner cases.
Phys- gaussian: Physics-integrated 3d gaussians for generative dynamics
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.
citing papers explorer
-
CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis
CARLA-GS is a modular pipeline that uses an LLM for semantic trajectory planning, CARLA for physics execution, and 3D Gaussian Splatting for photorealistic rendering to synthesize autonomous driving corner cases.
-
Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
Real2Sim reconstructs editable dynamic driving scenes as temporally continuous Gaussians integrated with a differentiable MPM physics solver for high-fidelity simulation of interactions and collisions.