# Estimation of Camera Response Function using Prediction Consistency and Gradual Refinement with an Extension to Deep Learning

arXiv: https://arxiv.org/abs/2010.04009 · HTML: https://mlsanity.com/paper/2010.04009/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Enhancing Visibility in Nighttime Haze Images Using Guided APSF and Gradient Adaptive Convolution](https://mlsanity.com/paper/2308.01738/) (2023)
- [Representing Camera Response Function by a Single Latent Variable and Fully Connected Neural Network](https://mlsanity.com/paper/2209.03624/) (2022)
- [Colour alignment for relative colour constancy via non-standard references](https://mlsanity.com/paper/2112.15106/) (2021)
- [Assessing the Role of Datasets in the Generalization of Motion Deblurring Methods to Real Images](https://mlsanity.com/paper/2209.12675/) (2022)
- [The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perception](https://mlsanity.com/paper/2506.02395/) (2025)

## Abstract (arXiv)

Most existing methods for CRF estimation from a single image fail to handle general real images. For instance, EdgeCRF based on colour patches extracted from edges works effectively only when the presence of noise is insignificant, which is not the case for many real images; and, CRFNet, a recent method based on fully supervised deep learning works only for the CRFs that are in the training data, and hence fail to deal with other possible CRFs beyond the training data. To address these problems, we introduce a non-deep-learning method using prediction consistency and gradual refinement. First, we rely more on the patches of the input image that provide more consistent predictions. If the predictions from a patch are more consistent, it means that the patch is likely to be less affected by noise or any inferior colour combinations, and hence, it can be more reliable for CRF estimation. Second, we employ a gradual refinement scheme in which we start from a simple CRF model to generate a result which is more robust to noise but less accurate, and then we gradually increase the model's complexity to improve the result. This is because a simple model, while being less accurate, overfits less to noise than a complex model does. Our experiments show that our method outperforms the existing single-image methods for daytime and nighttime real images. We further propose a more efficient deep learning extension that performs test-time training (based on unsupervised losses) on the test input image. This provides our method better generalization performance than CRFNet making it more practically applicable for CRF estimation for general real images.