TrafficImag: A Benchmark for Counterfactual Roadside Traffic Video Generation

arXiv:2609.30722 · cs.CV, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Actor — 109× in this paper · explained in 3 episodes
• Benchmark — 45× in this paper · explained in 2 episodes
• Hallucination — 7× in this paper · explained in 4 episodes
• World Model — 6× in this paper · explained in 7 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Failure Taxonomy — 4× in this paper · explained in 2 episodes
• Calibration — 3× in this paper · explained in 7 episodes
• Vision-language models — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Causal Reasoning — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Qwen2.5-VL Technical Report
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios
• GAIA-1: A Generative World Model for Autonomous Driving
• GPT-4o System Card
• LLaVA-OneVision: Easy Visual Task Transfer
• TrailBlazer: Trajectory Control for Diffusion-Based Video Generation
• FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
• Promptable Closed-loop Traffic Simulation
• DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
• ScenePilot-4K: A Large-Scale First-Person Dataset and Benchmark for Vision-Language Models in Autonomous Driving
• ARCAS: An Augmented Reality Collision Avoidance System with SLAM-Based Tracking for Enhancing VRU Safety
• EgoTraj: Real-World Egocentric Human Trajectory Dataset for Multimodal Prediction
• Qwen-Image-2.0 Technical Report
• DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

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