# "Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors

arXiv: https://arxiv.org/abs/1812.00467 · HTML: https://mlsanity.com/paper/1812.00467/

## Key facts

- Cited by 114 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2018.

## Built on by (most cited first, 30 of 114)

- [Self-supervised Video Object Segmentation by Motion Grouping](https://mlsanity.com/paper/2104.07658/) (2021)
- [NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstruction](https://mlsanity.com/paper/2108.10991/) (2021)
- [HNeRV: A Hybrid Neural Representation for Videos](https://mlsanity.com/paper/2304.02633/) (2023)
- [Flow-based Kernel Prior with Application to Blind Super-Resolution](https://mlsanity.com/paper/2103.15977/) (2021)
- [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022)
- [Segmenting Moving Objects via an Object-Centric Layered Representation](https://mlsanity.com/paper/2207.02206/) (2022)
- [Explore Image Deblurring via Blur Kernel Space](https://mlsanity.com/paper/2104.00317/) (2021)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Early Stopping for Deep Image Prior](https://mlsanity.com/paper/2112.06074/) (2021)
- [On Measuring and Controlling the Spectral Bias of the Deep Image Prior](https://mlsanity.com/paper/2107.01125/) (2021)
- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)
- [DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration](https://mlsanity.com/paper/2303.06682/) (2023)
- [De-rendering the World's Revolutionary Artefacts](https://mlsanity.com/paper/2104.03954/) (2021)
- [Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal](https://mlsanity.com/paper/2207.08178/) (2022)
- [A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning](https://mlsanity.com/paper/2106.03323/) (2021)
- [Internal Video Inpainting by Implicit Long-range Propagation](https://mlsanity.com/paper/2108.01912/) (2021)
- [Neural Image Representations for Multi-Image Fusion and Layer Separation](https://mlsanity.com/paper/2108.01199/) (2021)
- [Blind Image Decomposition](https://mlsanity.com/paper/2108.11364/) (2021)
- [Deep Video Prior for Video Consistency and Propagation](https://mlsanity.com/paper/2201.11632/) (2022)
- [Test-Time Degradation Adaptation for Open-Set Image Restoration](https://mlsanity.com/paper/2312.02197/) (2023)
- [Detector-Free Weakly Supervised Grounding by Separation](https://mlsanity.com/paper/2104.09829/) (2021)
- [Unsupervised Portrait Shadow Removal via Generative Priors](https://mlsanity.com/paper/2108.03466/) (2021)
- [Neural Spline Fields for Burst Image Fusion and Layer Separation](https://mlsanity.com/paper/2312.14235/) (2023)
- [DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos](https://mlsanity.com/paper/2405.17705/) (2024)
- [Self-Validation: Early Stopping for Single-Instance Deep Generative Priors](https://mlsanity.com/paper/2110.12271/) (2021)
- [A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution](https://mlsanity.com/paper/2404.15620/) (2024)
- [Visible Watermark Removal via Self-calibrated Localization and Background Refinement](https://mlsanity.com/paper/2108.03581/) (2021)
- [PetsGAN: Rethinking Priors for Single Image Generation](https://mlsanity.com/paper/2203.01488/) (2022)
- [Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior](https://mlsanity.com/paper/2210.05361/) (2022)
- [SinIR: Efficient General Image Manipulation with Single Image Reconstruction](https://mlsanity.com/paper/2106.07140/) (2021)

## Abstract (arXiv)

Many seemingly unrelated computer vision tasks can be viewed as a special case of image decomposition into separate layers. For example, image segmentation (separation into foreground and background layers); transparent layer separation (into reflection and transmission layers); Image dehazing (separation into a clear image and a haze map), and more. In this paper we propose a unified framework for unsupervised layer decomposition of a single image, based on coupled "Deep-image-Prior" (DIP) networks. It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image. We show that coupling multiple such DIPs provides a powerful tool for decomposing images into their basic components, for a wide variety of applications. This capability stems from the fact that the internal statistics of a mixture of layers is more complex than the statistics of each of its individual components. We show the power of this approach for Image-Dehazing, Fg/Bg Segmentation, Watermark-Removal, Transparency Separation in images and video, and more. These capabilities are achieved in a totally unsupervised way, with no training examples other than the input image/video itself.