# DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

arXiv: https://arxiv.org/abs/2012.00595 · HTML: https://mlsanity.com/paper/2012.00595/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2020.

## Built on by (most cited first, 16 of 16)

- [Blur Interpolation Transformer for Real-World Motion from Blur](https://mlsanity.com/paper/2211.11423/) (2022)
- [Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance](https://mlsanity.com/paper/2207.10123/) (2022)
- [Motion-from-Blur: 3D Shape and Motion Estimation of Motion-blurred Objects in Videos](https://mlsanity.com/paper/2111.14465/) (2021)
- [LAVIB: A Large-scale Video Interpolation Benchmark](https://mlsanity.com/paper/2406.09754/) (2024)
- [Recent Advances on Non-Line-of-Sight Imaging: Conventional Physical Models, Deep Learning, and New Scenes](https://mlsanity.com/paper/2104.13807/) (2021)
- [Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects](https://mlsanity.com/paper/2106.08762/) (2021)
- [Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding](https://mlsanity.com/paper/2303.15417/) (2023)
- [Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey](https://mlsanity.com/paper/2405.01725/) (2024)
- [Finding Geometric Models by Clustering in the Consensus Space](https://mlsanity.com/paper/2103.13875/) (2021)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Human from Blur: Human Pose Tracking from Blurry Images](https://mlsanity.com/paper/2303.17209/) (2023)
- [H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System](https://mlsanity.com/paper/2208.02436/) (2022)
- [Benchmarking EfficientTAM on FMO datasets](https://mlsanity.com/paper/2509.06536/) (2025)
- [Lightweight High-Speed Photography Built on Coded Exposure and Implicit Neural Representation of Videos](https://mlsanity.com/paper/2311.13134/) (2023)
- [Retrieval Robust to Object Motion Blur](https://mlsanity.com/paper/2404.18025/) (2024)
- [Recovering 3D Shapes from Ultra-Fast Motion-Blurred Images](https://mlsanity.com/paper/2602.07860/) (2026)

## Abstract (arXiv)

Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In such cases, classical methods, or even humans, are unable to recover the object's appearance and motion. We propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i.e. temporal super-resolution). The proposed generative model embeds an image of the blurred object into a latent space representation, disentangles the background, and renders the sharp appearance. Inspired by the image formation model, we design novel self-supervised loss function terms that boost performance and show good generalization capabilities. The proposed DeFMO method is trained on a complex synthetic dataset, yet it performs well on real-world data from several datasets. DeFMO outperforms the state of the art and generates high-quality temporal super-resolution frames.