Update README.md

README.md

@@ -1,7 +1,6 @@
 ---
 language:
 - en
-license: mit
 library_name: pytorch
 pipeline_tag: image-to-image
 tags:
@@ -45,104 +44,83 @@ model-index:
 
 # Multinex: Lightweight Low-Light Image Enhancement via Multi-prior Retinex
 
-**Multinex** is a lightweight **low-light image enhancement (LLIE)** model based on a **multi-prior Retinex** formulation. It is designed to improve **brightness, color fidelity, and structural detail** in dark images while remaining extremely compact and efficient.
+**Multinex** is a lightweight model for **low-light image enhancement**. It is designed to brighten dark images, recover clearer colors, and improve visible detail while staying very small and efficient.
 
-Multinex combines:
-- a **Retinex-guided residual enhancement formulation**
-- **analytic luminance and reflectance prior stacks**
-- a **dual-branch lightweight fusion network**
-
-This design allows the model to achieve strong perceptual enhancement quality and competitive paired-image restoration performance at a tiny parameter budget, including a lightweight version around **45K parameters** and an even smaller nano variant around **0.7K parameters**. The paper reports strong results on both enhancement and downstream detection benchmarks.  
-
-**Keywords:** low-light image enhancement, LLIE, Retinex, image restoration, lightweight neural network, edge deployment, exposure correction, color correction, perceptual image enhancement, real-time enhancement.
+Multinex is built around a simple idea: instead of relying only on raw RGB input, it uses multiple useful image cues related to brightness and color, then combines them through a compact network. This helps it perform strongly even at a very small model size.
 
 ## Model Description
 
-Many low-light image enhancement methods either:
-- use large neural networks that are hard to deploy on-device, or
-- operate in a single color space where illumination and color remain partially entangled.
-
-Multinex addresses this with a structured and lightweight design. Instead of learning a full reconstruction in a standard Retinex manner, it predicts an **enhancement delta** added to the input image. The correction is factorized into:
-- a **luminance correction**
-- a **reflectance correction**
+Many low-light enhancement methods are either large and expensive to run, or they struggle to separate brightness changes from color correction cleanly.
 
-The model also uses **analytic representation priors** to reduce the burden on the network. In particular:
-- the **luminance guidance stack** provides illumination-oriented cues
-- the **reflectance guidance stack** provides chromatic and color-structure cues
+Multinex addresses this with a lightweight and structured design. It uses:
+- a brightness-oriented branch
+- a color-oriented branch
+- compact fusion modules
+- carefully chosen analytic image priors
 
-This makes the model especially attractive for:
-- mobile or embedded deployment
-- lightweight computer vision pipelines
-- preprocessing for downstream tasks such as object detection in dark scenes
+These priors give the model a stronger starting point, so it does not need to learn everything from scratch.
 
 ## Why Multinex?
 
-Multinex is useful when you need a **small and efficient low-light enhancement model** without giving up physical interpretability.
+Multinex is useful when you want:
+- strong low-light enhancement
+- a small and efficient model
+- better brightness and color recovery
+- a method suitable for edge or real-time use
+- a practical preprocessing step for downstream vision tasks
 
 ### Main advantages
-- **Lightweight**: designed for very low parameter counts
-- **Retinex-inspired**: uses luminance/reflectance structure as a prior
-- **Analytic priors**: leverages hand-crafted luminance and chrominance descriptors
-- **Strong perceptual quality**: especially strong on no-reference perceptual metrics
-- **Practical utility**: enhancement can improve downstream visual tasks in low light
+- **Lightweight**: very small compared to many recent methods
+- **Efficient**: suitable for resource-constrained settings
+- **Structured**: uses separate cues for brightness and color
+- **Practical**: useful both for visual enhancement and downstream tasks
+- **Robust**: performs well across both reference and no-reference benchmarks
 
-## Architecture Overview
+## How It Works
 
-Multinex enhances an RGB input image through a residual Retinex-based formulation:
+Multinex takes a dark RGB image and improves it using two types of guidance:
+- **luminance guidance**, which helps with brightness
+- **reflectance guidance**, which helps with color and appearance
 
-\[
-\hat{\mathbf{I}} = \mathbf{I} + \Delta_{\mathbf{I}} = \mathbf{I} + \Delta_L \odot \Delta_R
-\]
+These two forms of guidance are processed by a lightweight network and combined into the final enhanced image.
 
-where:
-- \(\mathbf{I}\) is the low-light input image
-- \(\hat{\mathbf{I}}\) is the enhanced image
-- \(\Delta_L\) is the learned luminance correction
-- \(\Delta_R\) is the learned reflectance correction
+In simple terms, Multinex tries to answer two questions:
+- how should this image be brightened?
+- how should its colors and details be corrected?
 
-Instead of learning directly from raw RGB alone, Multinex constructs two analytic prior stacks:
-- **Luminance stack** for brightness-related structure
-- **Reflectance stack** for color and chromatic structure
-
-These stacks are processed by lightweight fusion modules to produce the correction terms.
+By handling these separately, the model can enhance low-light images more effectively.
 
 ## Prior Stacks
 
-A key idea in Multinex is that **the network should not need to rediscover useful image priors from scratch**.
+A key part of Multinex is its use of **prior stacks**.
 
 ### Luminance guidance stack
-The paper uses a luminance stack built from multiple analytic luminance descriptors, including variants such as:
-- Rec.709 luminance
-- max-based luminance
-- lightness-based luminance
-- L2-based luminance
+This stack provides different views of image brightness. It helps the model understand where the image is dark, how light is distributed, and how brightness should be adjusted.
 
 ### Reflectance guidance stack
-The reflectance stack uses complementary chromatic descriptors, including:
-- \(C_b, C_r\)
-- normalized chromaticities \(r, g\)
-- saturation \(S\)
+This stack provides different views of image color and chromatic structure. It helps the model better recover color, preserve regions, and reduce unwanted artifacts.
 
-The supplementary further motivates these choices with **Linear Reconstruction Analysis (LRA)** and descriptor-complementarity analysis.
+Together, these stacks give the model a richer and more stable representation of the image.
 
 ## Intended Uses
 
 ### Direct use
 - Enhance dark photos
-- Improve brightness and color visibility in low-light scenes
-- Preprocess images before downstream computer vision tasks
+- Improve brightness and color visibility
+- Recover clearer low-light images
+- Preprocess images before other vision tasks
 
 ### Downstream use
-- Machine Vision
+- Machine vision
 - Low-light object detection
-- Surveillance and nighttime vision preprocessing
-- Embedded or edge imaging systems
+- Surveillance and nighttime imaging
+- Embedded and edge systems
 - Mobile photography enhancement
-- Robotics and autonomous perception in dim environments
+- Robotics in dim environments
 
-## Training Data
+## Training and Evaluation Data
 
-The paper evaluates on common low-light image enhancement benchmarks, including:
+Multinex is evaluated on common low-light image enhancement benchmarks, including:
 - **LOL-v1**
 - **LOL-v2-real**
 - **LOL-v2-syn**
@@ -152,18 +130,17 @@ The paper evaluates on common low-light image enhancement benchmarks, including:
 - **NPE**
 - **ExDark** for downstream detection evaluation
 
-Please check the paper and codebase for the exact training split, preprocessing, and evaluation protocol used for each released checkpoint.
+Please refer to the paper and code for exact training details and evaluation settings.
 
 ## Performance
 
 The paper reports that Multinex:
-- outperforms prior lightweight and micro models in several settings
-- achieves strong no-reference perceptual performance
-- remains competitive relative to much larger methods
-- improves downstream object detection performance in low-light conditions
+- outperforms earlier lightweight and micro models in several settings
+- achieves strong no-reference perceptual quality
+- remains competitive with much larger methods
+- improves downstream object detection performance in low-light scenes
 
-### Example reported paired restoration results
-For the lightweight Multinex model, the paper reports:
+### Example paired restoration results
 
 | Dataset | PSNR | SSIM | LPIPS |
 |---|---:|---:|---:|
@@ -171,14 +148,29 @@ For the lightweight Multinex model, the paper reports:
 | LOL-v2-real | 23.04 | 0.860 | 0.178 |
 | LOL-v2-syn | 25.04 | 0.930 | 0.068 |
 
-### Example reported no-reference results
+### Example no-reference results
+
 | Metric | Mean |
 |---|---:|
 | NIQE ↓ | 3.64 |
 | BRISQUE ↓ | 15.89 |
 
 ### Efficiency
+
 | Variant | Parameters | GFLOPs |
 |---|---:|---:|
 | Multinex | 0.0447M | 2.50 |
 | Multinex-Nano | 0.0007M | very low |
+
+
+## Citation
+
+If you use Multinex in your work, please cite the paper.
+
+```bibtex
+@inproceedings{multinex2026,
+  title     = {Multinex: Lightweight Low-light Image Enhancement via Multi-prior Retinex},
+  author    = {Alexandru Brateanu and Tingting Mu and Codruta O. Ancuti and Cosmin Ancuti},
+  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+  year      = {2026}
+}