Revisiting Image Fusion for Multi-Illuminant White-Balance Correction.
In ICCV, 2025.

David Serrano-Lozano^1,2, Aditya Arora^3,4,5, Luis Herranz⁶,
Konstantinos G. Derpanis^3,4, Michael S. Brown³ and Javier Vazquez-Corral<sup>1,2

1</sup>Computer Vision Center, ²Universitat Autònoma de Barcelona, ³York University,
⁴Vector Institute, ⁵TU Darmstadt and ⁶Universidad Politécnica de Madrid

---

TODOs (In Progress)

• Upload models for both splits of our dataset and RenderedWB.
• Upload the dataset. We are currently exploring the best way to host it.

Method

We propose a lightweight Transformer block to blend five white balance (WB) presets and produce a white-balanced image. Our model contains only 7.9K parameters.

Data

We repurpose the LSMI dataset to compute ground-truth white-balanced images from multi-illuminant scenes.

We are currently evaluating the best options for dataset hosting. It will be available for download soon.

Getting Started

Clone the repository and install the required dependencies.

Train and Inference

Pre-trained models are available in the weights folder. Each checkpoint is only ~38KB.

Both training and inference use the config.yaml file to specify all parameters and configurations. Please adapt it accordingly.

To run inference on our dataset:

python inference.py

To train a model:

python train.py