R3L

Reported on 3 benchmarks across 3 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical1 result

Image DenoisingonBSD68 sigma30
PSNR· 2021-07-12
27.67
SOTA
R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery arXiv:2107.05318

Computer Vision1 result

DenoisingonBSD68 sigma30
PSNR· 2021-07-12
27.67
best: 30.7 (Residual Dense Network +)
R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery arXiv:2107.05318

Adversarial1 result

3D ArchitectureonBSD68 sigma30
PSNR· 2021-07-12
27.67
best: 30.7 (Residual Dense Network +)
R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery arXiv:2107.05318