Secrets of Event-Based Optical Flow
This work addresses motion estimation for event-based vision systems, offering an incremental improvement over existing methods by adapting deep-learning principles to event data.
The paper tackles optical flow estimation from event cameras by extending the Contrast Maximization framework with key elements like objective function design and event warping, achieving first rank among unsupervised methods on the MVSEC benchmark and competitive results on DSEC.
Event cameras respond to scene dynamics and offer advantages to estimate motion. Following recent image-based deep-learning achievements, optical flow estimation methods for event cameras have rushed to combine those image-based methods with event data. However, it requires several adaptations (data conversion, loss function, etc.) as they have very different properties. We develop a principled method to extend the Contrast Maximization framework to estimate optical flow from events alone. We investigate key elements: how to design the objective function to prevent overfitting, how to warp events to deal better with occlusions, and how to improve convergence with multi-scale raw events. With these key elements, our method ranks first among unsupervised methods on the MVSEC benchmark, and is competitive on the DSEC benchmark. Moreover, our method allows us to expose the issues of the ground truth flow in those benchmarks, and produces remarkable results when it is transferred to unsupervised learning settings. Our code is available at https://github.com/tub-rip/event_based_optical_flow