v2e paper award CVPR workshop on event based vision

The Sensors group is proud to receive the finalist runner-up best paper award for our v2e paper from the third CVPR workshop on event based vision 

Congratulations to Yuhuang Hu!

Watch the awards, the entire day or the paper teasers. The best paper award went to the nice paper "Detecting Stable Keypoints from Events through Image Gradient Prediction".

Read the details of our v2e work in Y. Hu, S-C Liu, T. Delbruck “v2e: From video frames to realistic DVS event camera streams,” in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2021 [Online]. Available: http://arxiv.org/abs/2006.07722.

This paper includes the release of our new dataset MVSEC-NIGHTL21 which labeled cars from nighttime driving video.

The jury awarded the v2e paper with the citation "For providing an accurate simulation model of DVS pixels under low-light conditions and demonstrating how training using simulated low-light events can improve model performance. Low-light operation is often cited as a strength of event-based sensors and this work provides a valuable simulation and training tool to help the event-based sensing community deliver on this promise."

See the v2e project page for more information.