Papers/2609.10756
🧪 Test?View on arXiv

GRADE: Single-Frame Generative Radar Depth Estimation Under Visual Degradation

Not provided in the content

depth estimationradar technologygenerative modelsenvironmental robustness
2609.10756
Builder Relevance
80%
4h ago

Abstract

GRADE is a method that improves depth perception in challenging visual conditions using mmWave radar.

Reality Card

Core Claim

GRADE achieves a mean absolute error (MAE) of 0.303 m in clear scenes and 0.313 m under smoke, outperforming existing baselines.

Method / Result

Trained and evaluated on ~95K frames across 12 buildings, achieving an MAE of 0.303 m in clear scenes.

Limitations

The method's performance may vary significantly under different environmental conditions not covered in training.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers