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

11/18/2020
by   Feng Gao, et al.
0

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.

READ FULL TEXT

page 3

page 5

05/30/2021

Unsupervised Joint Learning of Depth, Optical Flow, Ego-motion from Video

Estimating geometric elements such as depth, camera motion, and optical ...
06/27/2018

CeMNet: Self-supervised learning for accurate continuous ego-motion estimation

In this paper, we propose a novel self-supervised learning model for est...
05/31/2022

D^2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video

Given a monocular video, segmenting and decoupling dynamic objects while...
06/26/2017

Deep Semantic Classification for 3D LiDAR Data

Robots are expected to operate autonomously in dynamic environments. Und...
03/02/2022

Instance-aware multi-object self-supervision for monocular depth prediction

This paper proposes a self-supervised monocular image-to-depth predictio...
10/04/2019

Two Stream Networks for Self-Supervised Ego-Motion Estimation

Learning depth and camera ego-motion from raw unlabeled RGB video stream...
02/17/2015

SA-CNN: Dynamic Scene Classification using Convolutional Neural Networks

The task of classifying videos of natural dynamic scenes into appropriat...