# BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration

arXiv: https://arxiv.org/abs/2011.01406 · HTML: https://mlsanity.com/paper/2011.01406/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 15 of 15)

- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [TAPE: Task-Agnostic Prior Embedding for Image Restoration](https://mlsanity.com/paper/2203.06074/) (2022)
- [RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection](https://mlsanity.com/paper/2302.12464/) (2023)
- [PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples](https://mlsanity.com/paper/2210.04866/) (2022)
- [Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks](https://mlsanity.com/paper/2106.00673/) (2021)
- [Lightening Anything in Medical Images](https://mlsanity.com/paper/2406.10236/) (2024)
- [Learning degraded image classification with restoration data fidelity](https://mlsanity.com/paper/2101.09606/) (2021)
- [Image Denoising with Control over Deep Network Hallucination](https://mlsanity.com/paper/2201.00429/) (2022)
- [VibrantLeaves: A principled parametric image generator for training deep restoration models](https://mlsanity.com/paper/2504.10201/) (2025)
- [Controllable Confidence-Based Image Denoising](https://mlsanity.com/paper/2106.09311/) (2021)
- [Towards Robust Drone Vision in the Wild](https://mlsanity.com/paper/2208.12655/) (2022)
- [Target Aware Poisson-Gaussian Noise Parameters Estimation from Noisy Images](https://mlsanity.com/paper/2210.12142/) (2022)
- [Fuzzy-Conditioned Diffusion and Diffusion Projection Attention Applied to Facial Image Correction](https://mlsanity.com/paper/2306.14891/) (2023)
- [VerA: Versatile Anonymization Applicable to Clinical Facial Photographs](https://mlsanity.com/paper/2312.02124/) (2023)
- [Computer-aided Colorization State-of-the-science: A Survey](https://mlsanity.com/paper/2410.02288/) (2024)

## Abstract (arXiv)

Classic image-restoration algorithms use a variety of priors, either implicitly or explicitly. Their priors are hand-designed and their corresponding weights are heuristically assigned. Hence, deep learning methods often produce superior image restoration quality. Deep networks are, however, capable of inducing strong and hardly predictable hallucinations. Networks implicitly learn to be jointly faithful to the observed data while learning an image prior; and the separation of original data and hallucinated data downstream is then not possible. This limits their wide-spread adoption in image restoration. Furthermore, it is often the hallucinated part that is victim to degradation-model overfitting. We present an approach with decoupled network-prior based hallucination and data fidelity terms. We refer to our framework as the Bayesian Integration of a Generative Prior (BIGPrior). Our method is rooted in a Bayesian framework and tightly connected to classic restoration methods. In fact, it can be viewed as a generalization of a large family of classic restoration algorithms. We use network inversion to extract image prior information from a generative network. We show that, on image colorization, inpainting and denoising, our framework consistently improves the inversion results. Our method, though partly reliant on the quality of the generative network inversion, is competitive with state-of-the-art supervised and task-specific restoration methods. It also provides an additional metric that sets forth the degree of prior reliance per pixel relative to data fidelity.