# On-Demand Learning for Deep Image Restoration

arXiv: https://arxiv.org/abs/1612.01380 · HTML: https://mlsanity.com/paper/1612.01380/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2016.

## Built on by (most cited first, 6 of 6)

- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior](https://mlsanity.com/paper/2407.04947/) (2024)
- [Revisiting Implicit Neural Representations in Low-Level Vision](https://mlsanity.com/paper/2304.10250/) (2023)
- [MRI Super-Resolution with Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2511.16854/) (2025)
- [Light Field Implicit Representation for Flexible Resolution Reconstruction](https://mlsanity.com/paper/2112.00185/) (2021)
- [A Scalable Training Strategy for Blind Multi-Distribution Noise Removal](https://mlsanity.com/paper/2310.20064/) (2023)

## Abstract (arXiv)

While machine learning approaches to image restoration offer great promise, current methods risk training models fixated on performing well only for image corruption of a particular level of difficulty---such as a certain level of noise or blur. First, we examine the weakness of conventional "fixated" models and demonstrate that training general models to handle arbitrary levels of corruption is indeed non-trivial. Then, we propose an on-demand learning algorithm for training image restoration models with deep convolutional neural networks. The main idea is to exploit a feedback mechanism to self-generate training instances where they are needed most, thereby learning models that can generalize across difficulty levels. On four restoration tasks---image inpainting, pixel interpolation, image deblurring, and image denoising---and three diverse datasets, our approach consistently outperforms both the status quo training procedure and curriculum learning alternatives.