TerrainForge: Physics-Grounded Road Geometry Editing for Counterfactual Autonomous Driving
cs.CV
Submitted: 2026-10-02
Updated: 2026-10-11
Sources
- muSync-GS: Physics-Synchronized Driving Video Synthesis for Weather and Geometric Road Hazards
- LTX-Video: Realtime Video Latent Diffusion
- Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
- CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis
- VACE: All-in-One Video Creation and Editing
- GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS
- RoadWeaver: Large-Scale Lane-Level HD Map Generation from Scratch for Autonomous Driving Simulation
- STRAP: Spatial-Temporal Risk-Attentive Vehicle Trajectory Prediction for Autonomous Driving
- World Simulation with Video Foundation Models for Physical AI
- Wan: Open and Advanced Large-Scale Video Generative Models
- Physical Informed Driving World Model
- Physics-Aware 3D Gaussian Editing for Driving Scene Generation
- Toward Physically Consistent Driving Video World Models under Challenging Trajectories
- SceneFactory: GPU-Accelerated Multi-Agent Driving Simulation with Physics-Based Vehicle Dynamics
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models