Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes
arXiv:2011.09369
Abstract
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots. However, the rigid projection computed by ego-motion cannot represent all scene points, such as points on moving objects, leading to false guidance in these regions. To address this problem, we propose an Attentional Separation-and-Aggregation Network (ASANet), which can learn to distinguish and extract the scene's static and dynamic characteristics via the attention mechanism. We further propose a novel MotionNet with an ASANet as the encoder, followed by two separate decoders, to estimate the camera's ego-motion and the scene's dynamic motion field. Then, we introduce an auto-selecting approach to detect the moving objects for dynamic-aware learning automatically. Empirical experiments demonstrate that our method can achieve the state-of-the-art performance on the KITTI benchmark.
accepted by CoRL2020
References in corpus (8)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks
- Deep Ordinal Regression Network for Monocular Depth Estimation
- Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation