# Attentional Separation-and-Aggregation Network for Self-supervised Depth-Pose Learning in Dynamic Scenes

arXiv: https://arxiv.org/abs/2011.09369 · HTML: https://mlsanity.com/paper/2011.09369/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depth](https://mlsanity.com/paper/2203.15174/) (2022)
- [Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2110.08192/) (2021)
- [Attentive and Contrastive Learning for Joint Depth and Motion Field Estimation](https://mlsanity.com/paper/2110.06853/) (2021)
- [RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes](https://mlsanity.com/paper/2303.04456/) (2023)
- [DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume](https://mlsanity.com/paper/2308.07225/) (2023)
- [Fractal Pyramid Networks](https://mlsanity.com/paper/2106.14694/) (2021)
- [Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2301.05871/) (2023)
- [Pixel-Wise Prediction based Visual Odometry via Uncertainty Estimation](https://mlsanity.com/paper/2208.08892/) (2022)
- [Hybrid Transformer Based Feature Fusion for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.11066/) (2022)
- [Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions](https://mlsanity.com/paper/2605.07945/) (2026)

## Abstract (arXiv)

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.