Real-time 3D scene layout from a single image using Convolutional Neural Networks

36 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “ect Detection Auto Drive F F Maturana and Scherer (2015a) Lidar 3D Conv Self-Labeled X Classiﬁcation Aerial FF FF Engelcke et al. (2016) 3D Lidar 3D Conv Benchmark X Object Detection Auto Drive FF FF Yang et al. (2016a) RGB CNN Self-Labeled X Segmentation SLAM FFF FFF Oliveira et al. (2016) RGB CNN ”
Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “Based on the success of Fully Convolutional Networks ( FCN ) (Long et al., 2015) on semantics segmentation, Yang et al. (2016a) built a CNN model to extract the ground and wall planes from a single image.”
Pop-up SLAM: Semantic monocular plane SLAM for low-texture environments (2016, methodology): “There are three main steps in [4] to generate 3D world: CNN ground segmentation (optionally with Conditional Random Field refinement), polyline fitting, and pop up 3D plane model.”