# Onion-Peel Networks for Deep Video Completion

arXiv: https://arxiv.org/abs/1908.08718 · HTML: https://mlsanity.com/paper/1908.08718/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2019.

## Built on by (most cited first, 30 of 46)

- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [ProPainter: Improving Propagation and Transformer for Video Inpainting](https://mlsanity.com/paper/2309.03897/) (2023)
- [Towards An End-to-End Framework for Flow-Guided Video Inpainting](https://mlsanity.com/paper/2204.02663/) (2022)
- [FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting](https://mlsanity.com/paper/2109.02974/) (2021)
- [Flow-Guided Transformer for Video Inpainting](https://mlsanity.com/paper/2208.06768/) (2022)
- [TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations](https://mlsanity.com/paper/2103.15982/) (2021)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Progressive Temporal Feature Alignment Network for Video Inpainting](https://mlsanity.com/paper/2104.03507/) (2021)
- [Occlusion-Aware Video Object Inpainting](https://mlsanity.com/paper/2108.06765/) (2021)
- [Decoupled Spatial-Temporal Transformer for Video Inpainting](https://mlsanity.com/paper/2104.06637/) (2021)
- [LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model](https://mlsanity.com/paper/2305.11577/) (2023)
- [Error Compensation Framework for Flow-Guided Video Inpainting](https://mlsanity.com/paper/2207.10391/) (2022)
- [Internal Video Inpainting by Implicit Long-range Propagation](https://mlsanity.com/paper/2108.01912/) (2021)
- [DeViT: Deformed Vision Transformers in Video Inpainting](https://mlsanity.com/paper/2209.13925/) (2022)
- [The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting](https://mlsanity.com/paper/2105.05332/) (2021)
- [Flow-Guided Video Inpainting with Scene Templates](https://mlsanity.com/paper/2108.12845/) (2021)
- [Deep Video Inpainting Detection](https://mlsanity.com/paper/2101.11080/) (2021)
- [GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding](https://mlsanity.com/paper/2201.08131/) (2022)
- [Image Inpainting via Iteratively Decoupled Probabilistic Modeling](https://mlsanity.com/paper/2212.02963/) (2022)
- [Hadamard product in deep learning: Introduction, Advances and Challenges](https://mlsanity.com/paper/2504.13112/) (2025)
- [Semi-Supervised Video Inpainting with Cycle Consistency Constraints](https://mlsanity.com/paper/2208.06807/) (2022)
- [Semantically Consistent Video Inpainting with Conditional Diffusion Models](https://mlsanity.com/paper/2405.00251/) (2024)
- [CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion Models](https://mlsanity.com/paper/2501.02355/) (2025)
- [Deep Face Video Inpainting via UV Mapping](https://mlsanity.com/paper/2109.00681/) (2021)
- [Feature-Aligned Video Raindrop Removal with Temporal Constraints](https://mlsanity.com/paper/2205.14574/) (2022)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting](https://mlsanity.com/paper/2301.10048/) (2023)
- [BVINet: Unlocking Blind Video Inpainting with Zero Annotations](https://mlsanity.com/paper/2502.01181/) (2025)
- [3DFill:Reference-guided Image Inpainting by Self-supervised 3D Image Alignment](https://mlsanity.com/paper/2211.04831/) (2022)
- [One-Shot Video Inpainting](https://mlsanity.com/paper/2302.14362/) (2023)

## Abstract (arXiv)

We propose the onion-peel networks for video completion. Given a set of reference images and a target image with holes, our network fills the hole by referring the contents in the reference images. Our onion-peel network progressively fills the hole from the hole boundary enabling it to exploit richer contextual information for the missing regions every step. Given a sufficient number of recurrences, even a large hole can be inpainted successfully. To attend to the missing information visible in the reference images, we propose an asymmetric attention block that computes similarities between the hole boundary pixels in the target and the non-hole pixels in the references in a non-local manner. With our attention block, our network can have an unlimited spatial-temporal window size and fill the holes with globally coherent contents. In addition, our framework is applicable to the image completion guided by the reference images without any modification, which is difficult to do with the previous methods. We validate that our method produces visually pleasing image and video inpainting results in realistic test cases.