# BP-DIP: A Backprojection based Deep Image Prior

arXiv: https://arxiv.org/abs/2003.05417 · HTML: https://mlsanity.com/paper/2003.05417/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance](https://mlsanity.com/paper/2312.16519/) (2023)
- [On Measuring and Controlling the Spectral Bias of the Deep Image Prior](https://mlsanity.com/paper/2107.01125/) (2021)
- [Deep Internal Learning: Deep Learning from a Single Input](https://mlsanity.com/paper/2312.07425/) (2023)
- [Image Restoration by Deep Projected GSURE](https://mlsanity.com/paper/2102.02485/) (2021)
- [PIP: Positional-encoding Image Prior](https://mlsanity.com/paper/2211.14298/) (2022)
- [Convergence and Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems](https://mlsanity.com/paper/2309.12128/) (2023)
- [Convergence Guarantees of Overparametrized Wide Deep Inverse Prior](https://mlsanity.com/paper/2303.11265/) (2023)
- [An Interpretation of Regularization by Denoising and its Application with the Back-Projected Fidelity Term](https://mlsanity.com/paper/2101.11599/) (2021)
- [MrSARP: A Hierarchical Deep Generative Prior for SAR Image Super-resolution](https://mlsanity.com/paper/2212.00069/) (2022)
- [Deep Learning CT Image Restoration using System Blur and Noise Models](https://mlsanity.com/paper/2407.14983/) (2024)
- [Implicit Regularization of the Deep Inverse Prior Trained with Inertia](https://mlsanity.com/paper/2506.02986/) (2025)

## Abstract (arXiv)

Deep neural networks are a very powerful tool for many computer vision tasks, including image restoration, exhibiting state-of-the-art results. However, the performance of deep learning methods tends to drop once the observation model used in training mismatches the one in test time. In addition, most deep learning methods require vast amounts of training data, which are not accessible in many applications. To mitigate these disadvantages, we propose to combine two image restoration approaches: (i) Deep Image Prior (DIP), which trains a convolutional neural network (CNN) from scratch in test time using the given degraded image. It does not require any training data and builds on the implicit prior imposed by the CNN architecture; and (ii) a backprojection (BP) fidelity term, which is an alternative to the standard least squares loss that is usually used in previous DIP works. We demonstrate the performance of the proposed method, termed BP-DIP, on the deblurring task and show its advantages over the plain DIP, with both higher PSNR values and better inference run-time.