# Video Deblurring via Semantic Segmentation and Pixel-Wise Non-Linear Kernel

arXiv: https://arxiv.org/abs/1708.03423 · HTML: https://mlsanity.com/paper/1708.03423/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2017.

## Built on by (most cited first, 19 of 19)

- [Deep Image Deblurring: A Survey](https://mlsanity.com/paper/2201.10700/) (2022)
- [Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes](https://mlsanity.com/paper/2108.09982/) (2021)
- [Towards Rolling Shutter Correction and Deblurring in Dynamic Scenes](https://mlsanity.com/paper/2104.01601/) (2021)
- [Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network](https://mlsanity.com/paper/2106.16028/) (2021)
- [Blur Interpolation Transformer for Real-World Motion from Blur](https://mlsanity.com/paper/2211.11423/) (2022)
- [Video Frame Interpolation without Temporal Priors](https://mlsanity.com/paper/2112.01161/) (2021)
- [Face Deblurring using Dual Camera Fusion on Mobile Phones](https://mlsanity.com/paper/2207.11617/) (2022)
- [Efficient Video Deblurring Guided by Motion Magnitude](https://mlsanity.com/paper/2207.13374/) (2022)
- [Restoration of Video Frames from a Single Blurred Image with Motion Understanding](https://mlsanity.com/paper/2104.09134/) (2021)
- [SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution](https://mlsanity.com/paper/2402.17133/) (2024)
- [SAPNet: Segmentation-Aware Progressive Network for Perceptual Contrastive Deraining](https://mlsanity.com/paper/2111.08892/) (2021)
- [Motion-Aware Animatable Gaussian Avatars Deblurring](https://mlsanity.com/paper/2411.16758/) (2024)
- [Deep Richardson-Lucy Deconvolution for Low-Light Image Deblurring](https://mlsanity.com/paper/2308.05543/) (2023)
- [Learning to Deblur Polarized Images](https://mlsanity.com/paper/2402.18134/) (2024)
- [Synergy Between Semantic Segmentation and Image Denoising via Alternate Boosting](https://mlsanity.com/paper/2102.12095/) (2021)
- [Affine-modeled video extraction from a single motion blurred image](https://mlsanity.com/paper/2104.03777/) (2021)
- [Frequency-domain Learning with Kernel Prior for Blind Image Deblurring](https://mlsanity.com/paper/2504.14664/) (2025)
- [Joint Video Enhancement with Deblurring, Super-Resolution, and Frame Interpolation Network](https://mlsanity.com/paper/2506.03892/) (2025)
- [Video Deblurring with Deconvolution and Aggregation Networks](https://mlsanity.com/paper/2506.04054/) (2025)

## Abstract (arXiv)

Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. Optical flow can be used for kernel estimation since it predicts motion trajectories. However, the estimates are often inaccurate in complex scenes at object boundaries, which are crucial in kernel estimation. In this paper, we exploit semantic segmentation in each blurry frame to understand the scene contents and use different motion models for image regions to guide optical flow estimation. While existing pixel-wise blur models assume that the blur kernel is the same as optical flow during the exposure time, this assumption does not hold when the motion blur trajectory at a pixel is different from the estimated linear optical flow. We analyze the relationship between motion blur trajectory and optical flow, and present a novel pixel-wise non-linear kernel model to account for motion blur. The proposed blur model is based on the non-linear optical flow, which describes complex motion blur more effectively. Extensive experiments on challenging blurry videos demonstrate the proposed algorithm performs favorably against the state-of-the-art methods.