PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding
This addresses the need for efficient panoptic segmentation in applications like autonomous driving and augmented reality, offering a practical speed and memory improvement over existing methods.
The paper tackles panoptic segmentation by proposing PanoNet, a framework that generates semantic and instance masks simultaneously without detection, achieving high panoptic quality on Cityscapes images in real-time with significantly faster speed than comparable methods.
We propose a simple, fast, and flexible framework to generate simultaneously semantic and instance masks for panoptic segmentation. Our method, called PanoNet, incorporates a clean and natural structure design that tackles the problem purely as a segmentation task without the time-consuming detection process. We also introduce position-sensitive embedding for instance grouping by accounting for both object's appearance and its spatial location. Overall, PanoNet yields high panoptic quality results of high-resolution Cityscapes images in real-time, significantly faster than all other methods with comparable performance. Our approach well satisfies the practical speed and memory requirement for many applications like autonomous driving and augmented reality.