HybridCC

Multi-Block-Attention-based Color Constancy

ECCV 2026
University of Greifswald, Germany
Abstract

Color constancy algorithms estimate and remove the effect of the illuminant from a captured image, enabling consistent color perception under varying illumination conditions. Learning-based methods achieve high accuracy but tend to be biased toward the spectral characteristics of training cameras. Traditional algorithms such as white-patch Retinex are computationally efficient and camera-independent, but underperform when scene statistics deviate from their assumptions. Therefore, in this paper, we propose a hybrid approach that combines classical assumptions with learned features. Our model processes images in a block-based manner through two complementary branches. The backbone branch extracts scene features and identify reliable regions for illuminant estimation. Guided by these saliency maps, the statistics branch computes per-block illumination priors using a soft maximum formulation that provides a differentiable approximation to the classical white-patch Retinex. Features from both branches are fused and refined through multi-head self-attention, which enables blocks to exchange information across the image, addressing the aggregation bias common to block-based methods. Experiments on five benchmarks demonstrate that our model achieves state-of-the-art performance with a compact architecture (~1.1 MB, ~2.2 ms per image) that requires no camera-specific calibration or metadata.

Input scene White-balanced result
❮❯
INPUT
OUTPUT
Method
Overview diagram of HybridCC

The backbone extracts a shared feature map that branches into a saliency head and a feature-processing path in parallel. The statistics branch uses the resulting saliency map to compute block-wise illumination priors. All branches are fused and fed into the illumination estimation module, which refines per-block representations through self-attention and produces the final illuminant estimate via weighted combination.

Reliable regions learned without supervision

A MobileNetV3-Small backbone extracts a feature map from the input image. From this shared feature map, a saliency head predicts per-pixel reliability weights, while a separate feature-processing path pools the same features into block-level representations. Since no explicit saliency supervision is provided, the saliency head learns to emphasize informative regions purely through the illuminant estimation objective.

InputSaliency MapOurs
Saliency stability across two different cameras
Visualization of saliency stability. Each row shows the same scene from INTEL-TAU, captured by two different DSLR cameras. Despite their different spectral sensitivities, the model attends to similar informative regions regardless of camera type.

Statistical Results

The model is evaluated using a leave-one-dataset-out strategy, together with a cross-sensor protocol. Training uses Gehler-Shi, NUS-8, Cube+, and INTEL-TAU. TA-AWB is held out entirely and used only to test camera generalization. In every evaluation, there is no camera overlap between the training and test sets.

The model achieves the lowest mean angular error on Gehler-Shi, NUS-8, Cube+, and INTEL-TAU, as well as on the NUS-8 cross-sensor protocol — improving over the closest prior SOTA by 5–8% mean error, and by up to 18% on the worst-25% cases.

/ / / / /
SIIE
2.77°
C5
2.50°
GCC
2.35°
Tra-CC
2.32°
CCMNet
2.23°
HybridCC
2.11°
Mean angular error ↓
Citation

If you find this work useful, please consider citing our paper:

@inproceedings{ulucan2026multiblock,
  title     = {Multi-Block-Attention-based Color Constancy},
  author    = {Ulucan, Oguzhan and Ulucan, Diclehan and Ebner, Marc},
  booktitle = {European Conference on Computer Vision (ECCV)},
  year      = {2026}
}