Benchmark RadarAI BENCHMARK PROFILE
π-SUB
Evaluates underwater image enhancement models using a synthetic paired dataset generated by a physics-informed framework with depth-dependent irradiance and Jerlov water types.
- Released
- 2026-08-11
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Offers a hyper-realistic and generalizable synthetic benchmark to close the synthetic-to-real gap for underwater image enhancement.
Motivation
This paper presents $\pi$-SUB, a physics-informed framework for generating synthetic underwater benchmark datasets that bridges the synthetic-to-real gap for Underwater Image Enhancement (UIE).
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.