Research Paper

Core Innovation

This paper introduces JustDepth, a single-stage radar-camera depth estimator trained solely with radar, camera, and single-scan LiDAR data. It aggregates radar returns into a fixed-width 1D representation to decouple runtime from point count, uses a Height Fusion Block for modality fusion, and applies a lightweight GNN for global depth propagation, achieving faster inference and reduced artifacts.

Why It Matters

Accurate and fast depth perception is critical for autonomous systems to navigate safely and efficiently. Existing methods often suffer from high latency or require complex multi-stage processing, limiting real-world deployment. JustDepth streamlines depth estimation, enhancing system responsiveness and scalability for automotive and robotics applications.

Potential Customers & Pain Points

• Autonomous vehicle manufacturers – Need low-latency accurate depth perception
• Robotics companies – Require robust sensor fusion for navigation
• ADAS providers – Seek scalable real-time depth estimation solutions.

Business Model

Licensing the JustDepth platform to automotive OEMs, ADAS providers, and robotics companies; offering integration support and custom model training services.

Competitive Landscape

• Waymo
• Tesla
• Mobileye
• Luminar
• Innoviz

Implementation Challenges

• Integration complexity with existing vehicle sensor suites
• Robustness under diverse environmental conditions
• Competition from established multi-sensor fusion solutions

Validation Strategy

• Benchmark JustDepth on public datasets like nuScenes against leading methods
• Pilot deployments with automotive partners for real-world testing
• Collect feedback on latency
• accuracy
• and artifact reduction in operational environments