SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
This addresses the computational inefficiency and complexity of running separate methods for geometric and semantic tasks in intelligent agents, though it is incremental as it combines existing tasks into a unified framework.
The authors tackled the problem of intelligent agents needing both geometric and semantic understanding by proposing SimVODIS, a neural architecture that simultaneously performs visual odometry, object detection, and instance segmentation in a single thread, outperforming or matching state-of-the-art performance in these tasks.
Intelligent agents need to understand the surrounding environment to provide meaningful services to or interact intelligently with humans. The agents should perceive geometric features as well as semantic entities inherent in the environment. Contemporary methods in general provide one type of information regarding the environment at a time, making it difficult to conduct high-level tasks. Moreover, running two types of methods and associating two resultant information requires a lot of computation and complicates the software architecture. To overcome these limitations, we propose a neural architecture that simultaneously performs both geometric and semantic tasks in a single thread: simultaneous visual odometry, object detection, and instance segmentation (SimVODIS). Training SimVODIS requires unlabeled video sequences and the photometric consistency between input image frames generates self-supervision signals. The performance of SimVODIS outperforms or matches the state-of-the-art performance in pose estimation, depth map prediction, object detection, and instance segmentation tasks while completing all the tasks in a single thread. We expect SimVODIS would enhance the autonomy of intelligent agents and let the agents provide effective services to humans.