Pothole Risk Assessment with Geometrically Grounded Vision Language Models
cs.CV
Submitted: 2026-11-11
Updated: 2026-11-11
Terminology
Sources
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- Gemini: A Family of Highly Capable Multimodal Models
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- Evaluation and Comparison of Visual Language Models for Transportation Engineering Problems
- Depth Anything V2
- Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
- A Comprehensive Survey on Segment Anything Model for Vision and Beyond
- Segment Anything in High Quality
- An Enhanced YOLOv8 Model for Real-Time and Accurate Pothole Detection and Measurement
- On a Formal Model of Safe and Scalable Self-driving Cars
- TinySAM: Pushing the Envelope for Efficient Segment Anything Model
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs