DeepLearning

1. Image Depth Prediction

GitHub related topic

• 2014 Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

  Authors: David Eigen, Christian Puhrsch and Rob Fergus

  first one to use CNN for monocular image depth estimation

  Code

• 2016 Deeper depth prediction with fully convolutional residual networks

  Authors: Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab

  improved with a fully convolutional model incorporating efficient residual up-sampling blocks

  Code

• 2017 Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum Inference

  Authors: Bo Li, Yuchao Dai, Mingyi He

  propose a deep end-to-end learning framework to tackle these challenges, which learns the direct mapping from a color image to the corresponding depth map

• 2017 Unsupervised monocular depth estimation with left-right consistency

  Authors: C. Godard, O. Mac Aodha, and G. J. Brostow.

  enables convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data

  Code

• 2017 A Compromise Principle in Deep Monocular Depth Estimation

  Authors: Huan Fu, Mingming Gong, Chaohui Wang, Dacheng Tao

  propose a regression-classification cascaded network (RCCN), which consists of a regression branch predicting a low spatial resolution continuous depth map and a classification branch predicting a high spatial resolution discrete depth map

• 2018 Deep Ordinal Regression Network for Monocular Depth Estimation

  Authors: Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Dacheng Tao

  To eliminate or at least largely reduce these problems, introduce a spacing-increasing discretization (SID) strategy to discretize depth and recast depth network learning as an ordinal regression problem

  Code

• 2018 Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries.

  Authors: Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani

  toward more accurate estimation with a focus on depth maps with higher spatial resolution, propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. Another is refined loss function.

  Code

• 2018 Deep attention-based classification network for robust depth prediction

  Authors: Ruibo Li, Ke Xian, Chunhua Shen, Zhiguo Cao, Hao Lu, Lingxiao Hang

  present deep attention-based classification (DABC) network for robust single image depth prediction

• Other Project

  • MonoDepth-FPN-PyTorch