/references

list of references

Deep Learning

Features Extractor

  • C. Szegedy : Going deeper with convolution (2014)

Pose Estimation

  • W. D : Vehicule Pose and Shape Estimation through Multiple Monocular Vision

  • (Overlapping images form different view points) Y. Furukawa : Multi-view stereo: A tutorial (2015)

  • (Using pairs) D. Scharstein : A taxomony and evaluation of dense two-frame stereo correspondence algorithms (2002)

  • N. Sunderhauf : On the performance of convnet features for place recognition

  • A. Kendall : Geometric loss function for camera pose regression with deep learning (2017)

  • A. Toshev : Deeppose : Human pose estimation via deep neural networks (2014)

  • Y. Li : Worldwide pose estimation using 3d points clouds

Structure from motion

  • S. Agarwal : Building rome in a day (2011)
  • N. Snavely : Photo tourism : exploiting photo collections in 3D (2006)
  • C. Wu : Toward linear-time incremental structure from motion (2013)

Depth Esimation

  • D. Xu : Structured Attention Guided Convolutional Neural fields for Monocular Depth Estimation

  • (temopral sequences) R. Ranftl : Dense monocular depth estimation in complex dynamic scenes (2016)

  • Z. Li : MegaDepth : Learning single-view Depth Prediction from internet Photos

  • V. Ravi Kumar : Monocular Fisheye Camera Depth Estimation Using Semi-supervised space Velodyne Data

  • D. Martins : Fusion of stereo and still monocular depth estimates in a self.supervised learning context

  • A. Atapour-Abarghouei : Real-time Monocular depth Estimation using synthetic data with Domain Adaptation via Image style transfer

  • D. Eigen : Depth map prediction from a single image using a multi-scale deep network

  • D. Eigen : Predicting depth, surface normals and semantic labels with a common multi-scale convolutional neural network (2015)

  • L. Ladicky : Pulling things out of perspective (2014)

  • F.Liu : Learning depth from single monocular images using deep convolutional neural fields

  • K.Chatfield : Return of the devil in the details : delving deep into convolutional nets (2014)

  • F. Ciurea : Systems and methods for performing depth estimation using image data from multiple spectral channels (2014)

  • F. Ma : Sparse-to-dense : Depth prediction from depth samples and single image

  • J. Liu : Neural Network prediction model of rolling force based on ReLU activation function (2016)

  • M. Liu : Discrete-Constinuous Depth estimation from a single image (2014)

  • R. Garg : Unsupervised CNN for single view depth estimation (2016)

  • J. Xie : Fully automatic 2d-to-3d video conversion with deep convolutional neural networks (2016)

Normal Estimation / Normal Orientation

  • R. J. Woodhom : Photometroc method for determining surface orientation from multiple images

Edge Detection

Y.Li : Unsupervised Learning of edges (2016)

Prediction video

  • C. FIn : Unsupervised Learning for physical interaction through video prediction (2016)

  • J. Oh : Action Conditional video prediction using deep networks in atari games (2012)

  • M. Mathiew : Deep multi-scale video predicting beyond Mean Square Error (2015)

  • A. X. Lee : Stochastic Adversarial Video Prediction

Optical flow

  • T. Brox : High Accuracy optical flow estimation based on a theory for wrapping (2004)
  • C. Zach : A duality based approach for realtime tv-l 1 optical flow (2007)
  • B.K. Horn : Determining optical flow

Transfer Learning

  • Y. Bengio : Representation learning : a review and new perpectives (2013)

  • J. Donahue : A deep convolutional activation feature for genetic visual recognition (2013)

  • M. Oquab : Learning and transfering mid-level image representations using convolutional neural networks (2014)

  • A. S. Razavian : CNN features off-the-shelf : on estourding baseline for recognition (2014)

Image Processing

  • A. Hore : Image quality metrics : PSNR vs SSIM

Normalization

  • J. Ba : Layer Normalization (2016)

Sequence modelling

  • V. Michalski : Modelling deep temporal dependencies with reccurent grammar cells (2014)

  • F. Fragkiadak : Learning predictive visual models of physics for playing billards (2016)

  • J. Walker : Dense optical flow prediction from a static image (2015)

  • S. Bai : Empirical evaluation of Generic Convolutional and Recurrent networks for sequence modelling (2018)

Stereo Matching

  • J. Pang : Zoom and Learn : Generalizing Deep Stereo Matching to Novel Domains

Localization and Mapping

  • M. Cummins : Probabilistic localization and mapping in the space of appearance (2008)

  • J. Shotton : Scene coordonate regression forests for camera relocalization in RGB-D images (2013)

  • P. Sermanet : Overfeat : Integrated recognition, localization and detection using convolutional neural network

  • J. Wang Coarse-to-fine vision-based localization by indexing scale-invariant features (2006)

Navigation

Space

  • (Static scene + changing lightning) A. Abrams : Heliometric stereo : Shape from sun position (2012)

  • L. Blackmore : Robust Execution for Stochastic Hybrid Systems : Algorithms for Control, Estimation and Learning (2008)

Vehicule dynamics

  • B. Mettler : System Identification of small-size unmanned helicopter dynamics (1999)

Reinforcement Learning

  • J. Subramanian : Renewal Monte Carlo : Renewal theory based reinforcement learning

  • Y. Bengio : Curriculum Learning

  • V. Levine : Guided Policy Search (2013)

  • Y. Xiang : Constrained online optical control for continuous-time non-linear system using neurodynamics programming

  • P. Medagam : Optimal control of non-linear systems using rbf neural network and adaptive kalman filter

  • S. Efforti : Optimal control problem via neural network

  • S. Levine : Exploring Deep and recurrent architecture for optimal control

  • T. Zhang : Learning deep control policies for autonomous aerialmvehicules with npc-guided policy search

  • E. Todorov : Optimality principles in sensiromotor control

Other

  • E. Jared Shanwell : Vision-Aided Absolute Trajectory Estimation Using an Unsupervised Deep network with Online Erro Correction

  • G. Panpandreou : PersonLab : Person Pose Estimation and Instance Segmentation with Botton Up Part Based Geometric Embedding Mode

  • J. Henriques : MapNet : An allocentric Spatial Memory for Mapping Environments

  • A. J. Davidson: FutureMapping : The computaitonal Structure of Spatial AI Systems

  • D. Jimemez Pezende : Unsupervised Learning of 3D Structure from Image