Benchmark RadarAI BENCHMARK PROFILE
IR275K
A benchmark for infrared multi-frame super-resolution containing 594 video sequences and 275,196 frames with fixed sequence-level splits and a reproducible x4 evaluation protocol.
- Released
- 2026-07-24
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Provides a standardized evaluation resource for accuracy-efficiency trade-offs in infrared MFSR, a domain with fragmented evaluation practices.
Motivation
Efficient processing is becoming increasingly important in infrared remote sensing, where satellite constellations produce large volumes of observations under constrained detector resolution, power, and downlink bandwidth.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.