# HyperCUT: Video Sequence from a Single Blurry Image using Unsupervised Ordering

arXiv: https://arxiv.org/abs/2304.01686 · HTML: https://mlsanity.com/paper/2304.01686/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 32 references that are in the map.
- First posted on arXiv 4 Apr 2023.

## Builds on (most cited first, 22 of 22)

- [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)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Deep multi-scale video prediction beyond mean square error](https://mlsanity.com/paper/1511.05440/) (2015)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [Real-Time High-Resolution Background Matting](https://mlsanity.com/paper/2012.07810/) (2020)
- [MediaPipe Hands: On-device Real-time Hand Tracking](https://mlsanity.com/paper/2006.10214/) (2020)
- [Bringing a Blurry Frame Alive at High Frame-Rate with an Event Camera](https://mlsanity.com/paper/1811.10180/) (2018)
- [Explore Image Deblurring via Blur Kernel Space](https://mlsanity.com/paper/2104.00317/) (2021)
- [Learning to Extract a Video Sequence from a Single Motion-Blurred Image](https://mlsanity.com/paper/1804.04065/) (2018)
- [CDFI: Compression-Driven Network Design for Frame Interpolation](https://mlsanity.com/paper/2103.10559/) (2021)
- [Motion Deblurring with Real Events](https://mlsanity.com/paper/2109.13695/) (2021)
- [Bringing Alive Blurred Moments](https://mlsanity.com/paper/1804.02913/) (2018)
- [Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes](https://mlsanity.com/paper/2104.01601/) (2021)
- [Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance](https://mlsanity.com/paper/2207.10123/) (2022)

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

- [Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains](https://mlsanity.com/paper/2403.16205/) (2024)
- [Generating the Past, Present and Future from a Motion-Blurred Image](https://mlsanity.com/paper/2512.19817/) (2025)
- [Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model](https://mlsanity.com/paper/2507.13599/) (2025)
- [Unblur-SLAM: Dense Neural SLAM for Blurry Inputs](https://mlsanity.com/paper/2603.26810/) (2026)
- [BluRef: Unsupervised Image Deblurring with Dense-Matching References](https://mlsanity.com/paper/2603.14176/) (2026)
- [PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video](https://mlsanity.com/paper/2610.01279/) (2026)

## Abstract (arXiv)

We consider the challenging task of training models for image-to-video deblurring, which aims to recover a sequence of sharp images corresponding to a given blurry image input. A critical issue disturbing the training of an image-to-video model is the ambiguity of the frame ordering since both the forward and backward sequences are plausible solutions. This paper proposes an effective self-supervised ordering scheme that allows training high-quality image-to-video deblurring models. Unlike previous methods that rely on order-invariant losses, we assign an explicit order for each video sequence, thus avoiding the order-ambiguity issue. Specifically, we map each video sequence to a vector in a latent high-dimensional space so that there exists a hyperplane such that for every video sequence, the vectors extracted from it and its reversed sequence are on different sides of the hyperplane. The side of the vectors will be used to define the order of the corresponding sequence. Last but not least, we propose a real-image dataset for the image-to-video deblurring problem that covers a variety of popular domains, including face, hand, and street. Extensive experimental results confirm the effectiveness of our method. Code and data are available at https://github.com/VinAIResearch/HyperCUT.git