# Joint Demosaicking and Denoising in the Wild: The Case of Training Under Ground Truth Uncertainty

arXiv: https://arxiv.org/abs/2101.04442 · HTML: https://mlsanity.com/paper/2101.04442/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Variational Denoising Network: Toward Blind Noise Modeling and Removal](https://mlsanity.com/paper/1908.11314/) (2019)
- [Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks](https://mlsanity.com/paper/1803.05215/) (2018)
- [Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation](https://mlsanity.com/paper/1904.12945/) (2019)
- [XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappings](https://mlsanity.com/paper/1711.05139/) (2017)
- [Iterative Joint Image Demosaicking and Denoising using a Residual Denoising Network](https://mlsanity.com/paper/1807.06403/) (2018)
- [A Review of an Old Dilemma: Demosaicking First, or Denoising First?](https://mlsanity.com/paper/2004.11577/) (2020)
- [Learning Deep Convolutional Networks for Demosaicing](https://mlsanity.com/paper/1802.03769/) (2018)

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

- [Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors](https://mlsanity.com/paper/2307.10667/) (2023)
- [Toward Moir'e-Free and Detail-Preserving Demosaicking](https://mlsanity.com/paper/2305.08585/) (2023)
- [Uncertainty-Driven Multi-Scale Feature Fusion Network for Real-time Image Deraining](https://mlsanity.com/paper/2307.09728/) (2023)
- [Combining Pre- and Post-Demosaicking Noise Removal for RAW Video](https://mlsanity.com/paper/2410.02572/) (2024)
- [Frequency Enhancement for Image Demosaicking](https://mlsanity.com/paper/2503.15800/) (2025)

## Abstract (arXiv)

Image demosaicking and denoising are the two key fundamental steps in digital camera pipelines, aiming to reconstruct clean color images from noisy luminance readings. In this paper, we propose and study Wild-JDD, a novel learning framework for joint demosaicking and denoising in the wild. In contrast to previous works which generally assume the ground truth of training data is a perfect reflection of the reality, we consider here the more common imperfect case of ground truth uncertainty in the wild. We first illustrate its manifestation as various kinds of artifacts including zipper effect, color moire and residual noise. Then we formulate a two-stage data degradation process to capture such ground truth uncertainty, where a conjugate prior distribution is imposed upon a base distribution. After that, we derive an evidence lower bound (ELBO) loss to train a neural network that approximates the parameters of the conjugate prior distribution conditioned on the degraded input. Finally, to further enhance the performance for out-of-distribution input, we design a simple but effective fine-tuning strategy by taking the input as a weakly informative prior. Taking into account ground truth uncertainty, Wild-JDD enjoys good interpretability during optimization. Extensive experiments validate that it outperforms state-of-the-art schemes on joint demosaicking and denoising tasks on both synthetic and realistic raw datasets.