# Exploiting Optical Flow Guidance for Transformer-Based Video Inpainting

arXiv: https://arxiv.org/abs/2301.10048 · HTML: https://mlsanity.com/paper/2301.10048/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 59 of its 80 references that are in the map.
- First posted on arXiv 24 Jan 2023.

## Builds on (most cited first, 30 of 59)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Deformable ConvNets v2: More Deformable, Better Results](https://mlsanity.com/paper/1811.11168/) (2018)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Image Inpainting for Irregular Holes Using Partial Convolutions](https://mlsanity.com/paper/1804.07723/) (2018)
- [Conditional Positional Encodings for Vision Transformers](https://mlsanity.com/paper/2102.10882/) (2021)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark](https://mlsanity.com/paper/1809.03327/) (2018)
- [MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers](https://mlsanity.com/paper/2012.00759/) (2020)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Learning Blind Video Temporal Consistency](https://mlsanity.com/paper/1808.00449/) (2018)
- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)

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

- [Transformer-based Generative Adversarial Networks in Computer Vision: A Comprehensive Survey](https://mlsanity.com/paper/2302.08641/) (2023)
- [Transformer-based Image and Video Inpainting: Current Challenges and Future Directions](https://mlsanity.com/paper/2407.00226/) (2024)
- [Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework](https://mlsanity.com/paper/2507.22481/) (2025)
- [Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques](https://mlsanity.com/paper/2401.17883/) (2024)
- [VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models](https://mlsanity.com/paper/2501.12267/) (2025)
- [Burst Image Super-Resolution via Multi-Cross Attention Encoding and Multi-Scan State-Space Decoding](https://mlsanity.com/paper/2505.19668/) (2025)

## Abstract (arXiv)

Transformers have been widely used for video processing owing to the multi-head self attention (MHSA) mechanism. However, the MHSA mechanism encounters an intrinsic difficulty for video inpainting, since the features associated with the corrupted regions are degraded and incur inaccurate self attention. This problem, termed query degradation, may be mitigated by first completing optical flows and then using the flows to guide the self attention, which was verified in our previous work - flow-guided transformer (FGT). We further exploit the flow guidance and propose FGT++ to pursue more effective and efficient video inpainting. First, we design a lightweight flow completion network by using local aggregation and edge loss. Second, to address the query degradation, we propose a flow guidance feature integration module, which uses the motion discrepancy to enhance the features, together with a flow-guided feature propagation module that warps the features according to the flows. Third, we decouple the transformer along the temporal and spatial dimensions, where flows are used to select the tokens through a temporally deformable MHSA mechanism, and global tokens are combined with the inner-window local tokens through a dual perspective MHSA mechanism. FGT++ is experimentally evaluated to be outperforming the existing video inpainting networks qualitatively and quantitatively.