# Learning to Synthesize Motion Blur

arXiv: https://arxiv.org/abs/1811.11745 · HTML: https://mlsanity.com/paper/1811.11745/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 30 of 37)

- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)
- [Video Frame Interpolation Transformer](https://mlsanity.com/paper/2111.13817/) (2021)
- [3D Common Corruptions and Data Augmentation](https://mlsanity.com/paper/2203.01441/) (2022)
- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [From Shadow Generation to Shadow Removal](https://mlsanity.com/paper/2103.12997/) (2021)
- [Realistic Blur Synthesis for Learning Image Deblurring](https://mlsanity.com/paper/2202.08771/) (2022)
- [MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting](https://mlsanity.com/paper/2203.06304/) (2022)
- [Sparse Global Matching for Video Frame Interpolation with Large Motion](https://mlsanity.com/paper/2404.06913/) (2024)
- [Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring](https://mlsanity.com/paper/2112.05150/) (2021)
- [Blur Interpolation Transformer for Real-World Motion from Blur](https://mlsanity.com/paper/2211.11423/) (2022)
- [Factorized Diffusion: Perceptual Illusions by Noise Decomposition](https://mlsanity.com/paper/2404.11615/) (2024)
- [Splatting-based Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/2201.10075/) (2022)
- [EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolation](https://mlsanity.com/paper/2503.15831/) (2025)
- [Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring](https://mlsanity.com/paper/2104.12665/) (2021)
- [JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting](https://mlsanity.com/paper/2107.04281/) (2021)
- [Learning to Adversarially Blur Visual Object Tracking](https://mlsanity.com/paper/2107.12085/) (2021)
- [Neighbor Correspondence Matching for Flow-based Video Frame Synthesis](https://mlsanity.com/paper/2207.06763/) (2022)
- [Restoration of Video Frames from a Single Blurred Image with Motion Understanding](https://mlsanity.com/paper/2104.09134/) (2021)
- [Bimodal SegNet: Instance Segmentation Fusing Events and RGB Frames for Robotic Grasping](https://mlsanity.com/paper/2303.11228/) (2023)
- [PolarAnything: Diffusion-based Polarimetric Image Synthesis](https://mlsanity.com/paper/2507.17268/) (2025)
- [DINO-Detect: A Simple yet Effective Framework for Blur-Robust AI-Generated Image Detection](https://mlsanity.com/paper/2511.12511/) (2025)
- [WorldGen: A Large Scale Generative Simulator](https://mlsanity.com/paper/2210.00715/) (2022)
- [Learning Global-aware Kernel for Image Harmonization](https://mlsanity.com/paper/2305.11676/) (2023)
- [Benchmarking Video Frame Interpolation](https://mlsanity.com/paper/2403.17128/) (2024)
- [Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring](https://mlsanity.com/paper/2204.12139/) (2022)
- [On Motion Blur and Deblurring in Visual Place Recognition](https://mlsanity.com/paper/2412.07751/) (2024)
- [Learning Spatio-Temporal Downsampling for Effective Video Upscaling](https://mlsanity.com/paper/2203.08140/) (2022)
- [SPEED: One-Step Pixel Diffusion for High-quality Video Frame Interpolation](https://mlsanity.com/paper/2607.15585/) (2026)
- [Human and Scene Motion Deblurring using Pseudo-blur Synthesizer](https://mlsanity.com/paper/2111.12911/) (2021)
- [Degradation-based augmented training for robust individual animal re-identification](https://mlsanity.com/paper/2603.04163/) (2026)

## Abstract (arXiv)

We present a technique for synthesizing a motion blurred image from a pair of unblurred images captured in succession. To build this system we motivate and design a differentiable "line prediction" layer to be used as part of a neural network architecture, with which we can learn a system to regress from image pairs to motion blurred images that span the capture time of the input image pair. Training this model requires an abundance of data, and so we design and execute a strategy for using frame interpolation techniques to generate a large-scale synthetic dataset of motion blurred images and their respective inputs. We additionally capture a high quality test set of real motion blurred images, synthesized from slow motion videos, with which we evaluate our model against several baseline techniques that can be used to synthesize motion blur. Our model produces higher accuracy output than our baselines, and is significantly faster than baselines with competitive accuracy.