PrNet: Efficient and Robust Phase Retrieval via Stochastic Refinement
35th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2025, İstanbul, Türkiye, 31 Ağustos - 03 Eylül 2025, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/mlsp62443.2025.11204288
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: computational imaging, deep learning, diffusion models, inverse problems, Phase retrieval
- Orta Doğu Teknik Üniversitesi Adresli: Evet
Özet
Phase retrieval is a fundamental inverse problem that arises in many scientific and engineering disciplines, where the goal is to reconstruct a signal from intensity-only measurements. In this work, we develop prNet, a novel phase retrieval framework that stochastically refines initial reconstructions with learned denoising and model-based updates. Our framework combines Langevin dynamics-based posterior sampling, adaptive noise schedule learning, warm-start initialization from classical solvers, and a progressive training strategy inspired by algorithm unrolling. By considering the perception-distortion tradeoff, our method also mitigates the over-smoothing effects commonly observed in prior approaches and enables reconstructions with fine details while minimizing artifacts. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in both efficiency and reconstruction quality.