Update README.md

README.md

@@ -1,3 +1,66 @@
----
-license: mit
----
+Bayesian Enhancement Model (BEM)
+
+AAAI 2026 — One-to-Many Modeling for Low-Light & Underwater Image Enhancement
+📄 Paper
+ | 💻 Code
+
+🌟 Overview
+
+Image enhancement is inherently one-to-many — a single degraded image often corresponds to multiple plausible enhanced outputs, especially in low-light and underwater environments.
+
+However, existing deterministic models can only produce one prediction, failing to capture this ambiguity.
+
+BEM (Bayesian Enhancement Model) solves this by:
+
+Modeling uncertainty using a Bayesian Neural Network (BNN)
+
+Generating multiple valid enhancement candidates
+
+Selecting or aggregating candidates via Ranking or Monte Carlo
+
+Refining details using a second-stage DNN
+
+Achieving DNN-level inference speed with BNN-level diversity
+
+This makes BEM the first practical Bayesian solution for large-scale image enhancement tasks.
+
+🔍 Key Features
+✓ One-to-Many Enhancement via Bayesian Inference
+
+BEM samples weights from a variational posterior learned by a Bayesian UNet.
+Each sample produces a distinct enhancement, capturing the ambiguity of the task 
+
+BNN_AAAI
+
+.
+
+✓ Two-Stage BNN → DNN Framework (Fast!)
+
+The core bottleneck is heavy BNN inference.
+So we introduce a coarse-to-fine pipeline:
+
+Stage I (BNN): Predict coarse latent results in low-dimensional space
+
+Stage II (DNN): Refine structural & texture details
+
+This yields a 22× speedup vs. vanilla BNNs (Fig.5 in paper) 
+
+BNN_AAAI
+
+.
+
+✓ Adaptive Prior for Stable Training
+
+Using EMA-updated parameters as priors accelerates convergence and reduces KL instability (Eq.6) 
+
+BNN_AAAI
+
+.
+
+✓ Two Inference Modes
+
+BEMRank — Select the best candidate using CLIP-IQA, NIQE, UIQM, or UCIQE
+
+BEMMC — Average multiple samples for stable, noise-free output
+
+Both modes outperform deterministic baselines.