# Improved Handling of Motion Blur in Online Object Detection

arXiv: https://arxiv.org/abs/2011.14448 · HTML: https://mlsanity.com/paper/2011.14448/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2020.

## Built on by (most cited first, 18 of 18)

- [SODFormer: Streaming Object Detection with Transformer Using Events and Frames](https://mlsanity.com/paper/2308.04047/) (2023)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [Egocentric Human-Object Interaction Detection Exploiting Synthetic Data](https://mlsanity.com/paper/2204.07061/) (2022)
- [An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains](https://mlsanity.com/paper/2402.17562/) (2024)
- [Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection](https://mlsanity.com/paper/2208.03062/) (2022)
- [Application of Ghost-DeblurGAN to Fiducial Marker Detection](https://mlsanity.com/paper/2109.03379/) (2021)
- [Learning to Remove Wrinkled Transparent Film with Polarized Prior](https://mlsanity.com/paper/2403.04368/) (2024)
- [FICGen: Frequency-Inspired Contextual Disentanglement for Layout-driven Degraded Image Generation](https://mlsanity.com/paper/2509.01107/) (2025)
- [Segment Any-Quality Images with Generative Latent Space Enhancement](https://mlsanity.com/paper/2503.12507/) (2025)
- [Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations](https://mlsanity.com/paper/2309.13150/) (2023)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark](https://mlsanity.com/paper/2503.17027/) (2025)
- [RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images](https://mlsanity.com/paper/2201.02314/) (2022)
- [Retrieval Robust to Object Motion Blur](https://mlsanity.com/paper/2404.18025/) (2024)
- [Motion Blur Robust Wheat Pest Damage Detection with Dynamic Fuzzy Feature Fusion](https://mlsanity.com/paper/2601.03046/) (2026)
- [Certified Training for Convolutional Perturbations](https://mlsanity.com/paper/2607.18195/) (2026)
- [Neuromorphic Object Detection: An In-Depth Study and Future Directions](https://mlsanity.com/paper/2607.23576/) (2026)
- [ENet-GP: Unified Document Image Restoration](https://mlsanity.com/paper/2609.33758/) (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 wish to detect specific categories of objects, for online vision systems that will run in the real world. Object detection is already very challenging. It is even harder when the images are blurred, from the camera being in a car or a hand-held phone. Most existing efforts either focused on sharp images, with easy to label ground truth, or they have treated motion blur as one of many generic corruptions. Instead, we focus especially on the details of egomotion induced blur. We explore five classes of remedies, where each targets different potential causes for the performance gap between sharp and blurred images. For example, first deblurring an image changes its human interpretability, but at present, only partly improves object detection. The other four classes of remedies address multi-scale texture, out-of-distribution testing, label generation, and conditioning by blur-type. Surprisingly, we discover that custom label generation aimed at resolving spatial ambiguity, ahead of all others, markedly improves object detection. Also, in contrast to findings from classification, we see a noteworthy boost by conditioning our model on bespoke categories of motion blur. We validate and cross-breed the different remedies experimentally on blurred COCO images and real-world blur datasets, producing an easy and practical favorite model with superior detection rates.