Self-Supervised Monocular Depth Estimation in Autonomous Driving

source
source: Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
source: DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency

Unsupervised Learning of Depth and Ego-Motion from Video

source
source
source
source
source
source

Digging Into Self-Supervised Monocular Depth Estimation

source
  • A novel appearance matching loss to address the problem of occluded pixels that occur when using monocular supervision.
  • A novel and simple auto-masking approach to ignore pixels where no relative camera motion is observed in monocular training.
  • A multi-scale appearance matching loss that performs all image sampling at the input resolution, leading to a reduction in depth artifacts

--

--

--

I’m a Ph.D. student at the Intelligent Robotics Group at Aalto University working on self-driving cars, reinforcement learning, and machine learning.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

The Beginner’s Guide to Preparing Text Data for Natural Language Processing

Multipath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction

NLP & Numeracy (Pt 1) —  Calculators for Natural Language

Customer Segmentation and Acquisition: A Machine Learning Approach

Spark: Resilient Distributed Datasets: A Fault-Tolerant Abstraction for In-Memory Cluster Computing

Spatial Transformer Network

Gated Recurrent Units explained with matrices: Part 2 Training and Loss Function

When Machine Learning meets Big Data

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Isaac Kargar

Isaac Kargar

I’m a Ph.D. student at the Intelligent Robotics Group at Aalto University working on self-driving cars, reinforcement learning, and machine learning.

More from Medium

Implementing Lane Detection in CARLA using LaneNet

The Importance of Sensor Fusion for Autonomous Vehicles

Indoor Robot Localization with SLAM

How I Built a Real-Size Self-Driving Car from Scratch