Joint Future Semantic and Instance Segmentation Prediction [chapter]

Camille Couprie, Pauline Luc, Jakob Verbeek
2019 Lecture Notes in Computer Science  
The ability to predict what will happen next from observing the past is a key component of intelligence. Methods that forecast future frames were recently introduced towards better machine intelligence. However, predicting directly in the image color space seems an overly complex task, and predicting higher level representations using semantic or instance segmentation approaches were shown to be more accurate. In this work, we introduce a novel prediction approach that encodes instance and
more » ... tic segmentation information in a single representation based on distance maps. Our graph-based modeling of the instance segmentation prediction problem allows us to obtain temporal tracks of the objects as an optimal solution to a watershed algorithm. Our experimental results on the Cityscapes dataset present state-of-theart semantic segmentation predictions, and instance segmentation results outperforming a strong baseline based on optical flow.
doi:10.1007/978-3-030-11015-4_14 fatcat:r6srpgaw6vasdeg5l4ayzqqqca