Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera
By Liyuan Pan, C. Scheerlinck, Xin Yu, Richard I. Hartley, Miaomiao Liu, Yuchao Dai. Computer Vision and Pattern Recognition, 2018
325 citations recorded by the source corpus.
Event-based cameras can measure intensity changes (called ‘events’) with microsecond accuracy under high-speed motion and challenging lighting conditions. With the active pixel sensor (APS), the event camera allows simultaneous output of the intensity frames. However, the output images are captured at a relatively low frame-rate and often suffer from motion blur. A blurry image can be regarded as the integral of a sequence of latent images, while the events indicate the changes between the latent images. Therefore, we are able to model the blur-generation process by associating event data to a latent image. In this paper, we propose a simple and effective approach, the Event-based Double Integral (EDI) model, to reconstruct a high frame-rate, sharp video from a single blurry frame and its event data. The video generation is based on solving a simple non-convex optimization problem in a single scalar variable. Experimental results on both synthetic and real images demonstrate the superiority of our EDI model and optimization method in comparison to the state-of-the-art.
View Paper: https://www.semanticscholar.org/paper/50ddc50a8dcda5361b8050648eac6b8465dda496
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Davide Scaramuzza
- Guillermo Gallego
- Henri Rebecq
- Stefan Leutenegger
- Tobi Delbruck
- Andrew J. Davison
- Garrick Orchard
- Chiara Bartolozzi
Citations in the corpus
- DSEC: A Stereo Event Camera Dataset for Driving Scenarios (2021, unknown): “The fusion of frames and events has proven to be beneficial in several prior works [13], [14], [15], [16], [17].”
- Event-Based Vision: A Survey (2019, methodology): “The above interpretation may be taken into account to design physically-grounded event-based algorithms, such as [7], [23], [24], [28], [62], [63], [64], [65], as opposed to algorithms that simply process events as a collection of points with vague photometric meaning.”