# Representing Camera Response Function by a Single Latent Variable and Fully Connected Neural Network

arXiv: https://arxiv.org/abs/2209.03624 · HTML: https://mlsanity.com/paper/2209.03624/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 8 Sep 2022.

## Builds on (most cited first, 7 of 7)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Adversarial Autoencoders](https://mlsanity.com/paper/1511.05644/) (2015)
- [Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS](https://mlsanity.com/paper/1912.06059/) (2019)
- [Robust Anomaly Detection in Images using Adversarial Autoencoders](https://mlsanity.com/paper/1901.06355/) (2019)
- [An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges](https://mlsanity.com/paper/2005.10516/) (2020)
- [Online Photometric Calibration for Auto Exposure Video for Realtime Visual Odometry and SLAM](https://mlsanity.com/paper/1710.02081/) (2017)
- [Estimation of Camera Response Function using Prediction Consistency and Gradual Refinement with an Extension to Deep Learning](https://mlsanity.com/paper/2010.04009/) (2020)

## Built on by (most cited first, 1 of 1)

- [Assessing the Role of Datasets in the Generalization of Motion Deblurring Methods to Real Images](https://mlsanity.com/paper/2209.12675/) (2022)

## Abstract (arXiv)

Modelling the mapping from scene irradiance to image intensity is essential for many computer vision tasks. Such mapping is known as the camera response. Most digital cameras use a nonlinear function to map irradiance, as measured by the sensor to an image intensity used to record the photograph. Modelling of the response is necessary for the nonlinear calibration. In this paper, a new high-performance camera response model that uses a single latent variable and fully connected neural network is proposed. The model is produced using unsupervised learning with an autoencoder on real-world (example) camera responses. Neural architecture searching is then used to find the optimal neural network architecture. A latent distribution learning approach was introduced to constrain the latent distribution. The proposed model achieved state-of-the-art CRF representation accuracy in a number of benchmark tests, but is almost twice as fast as the best current models when performing the maximum likelihood estimation during camera response calibration due to the simple yet efficient model representation.