Learning Event-Based Motion Deblurring
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3317-3326
Abstract
Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras, however, fast motion can be captured as events at high frame rate, raising new opportunities to exploring effective solutions. In this paper, we start from a sequential formulation of event-based motion deblurring, then show how its optimization can be unfolded with a novel end-toend deep architecture. The proposed architecture is a convolutional recurrent neural network that integrates visual and temporal knowledge of both global and local scales in principled manner. To further improve the reconstruction, we propose a differentiable directional event filtering module to effectively extract rich boundary prior from the evolution of events. We conduct extensive experiments on the synthetic GoPro dataset and a large newly introduced dataset captured by a DAVIS240C camera. The proposed approach achieves state-of-the-art reconstruction quality, and generalizes better to handling real-world motion blur.Keywords
All Related Versions
This publication has 40 references indexed in Scilit:
- Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs2016
- Blind Image Deblurring Using Dark Channel Prior2016
- Simultaneous Optical Flow and Intensity Estimation from an Event Camera2016
- FlowNet: Learning Optical Flow with Convolutional Networks2015
- Learning a convolutional neural network for non-uniform motion blur removal2015
- Discriminative learning of iteration-wise priors for blind deconvolution2015
- A 240 × 180 130 dB 3 µs Latency Global Shutter Spatiotemporal Vision SensorIEEE Journal of Solid-State Circuits, 2014
- Reconstructing surfaces of particle-based fluids using anisotropic kernelsACM Transactions on Graphics, 2013
- Fast motion deblurringACM Transactions on Graphics, 2009
- A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision SensorIEEE Journal of Solid-State Circuits, 2008