Validate deployment efficiency beyond the RTX 3090

Validate the CPU, edge-device, and embedded-deployment efficiency, peak memory usage, and energy consumption of MDIRNET beyond the reported NVIDIA RTX 3090 runtime measurements.

Background

The paper reports runtime measurements only on an NVIDIA RTX 3090 GPU. It explicitly identifies CPU, edge, and embedded deployment efficiency, along with memory and energy requirements, as unresolved aspects that must be assessed before broader practical deployment of the Multi-Degradation Image Restoration Network (MDIRNET).

References

All runtime measurements were conducted on an NVIDIA RTX~3090; CPU, edge, and embedded deployment efficiency, peak memory, and energy consumption remain unvalidated.

— MDIRNET: Multi-Degradation Image Restoration Network via Deep Unfolding  (2610.01655 - Nadeem et al., 1 Oct 2026) in Section Conclusion