• Home
  • Search
  • Temporally Consistent Depth Map Prediction Using Deep Convolutional Neural Network and Spatial-Temporal Conditional Random Field
  • Cite Icon2
  • https://doi.org/10.1007/s11390-017-1735-xCopy DOI Icon

Temporally Consistent Depth Map Prediction Using Deep Convolutional Neural Network and Spatial-Temporal Conditional Random Field

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep convolutional neural networks (DCNNs) based methods recently keep setting new records on the tasks of predicting depth maps from monocular images. When dealing with video-based applications such as 2D (2-dimensional) to 3D (3-dimensional) video conversion, however, these approaches tend to produce temporally inconsistent depth maps, since their CNN models are optimized over single frames. In this paper, we address this problem by introducing a novel spatial-temporal conditional random fields (CRF) model into the DCNN architecture, which is able to enforce temporal consistency between depth map estimations over consecutive video frames. In our approach, temporally consistent superpixel (TSP) is first applied to an image sequence to establish the correspondence of targets in consecutive frames. A DCNN is then used to regress the depth value of each temporal superpixel, followed by a spatial-temporal CRF layer to model the relationship of the estimated depths in both spatial and temporal domains. The parameters in both DCNN and CRF models are jointly optimized with back propagation. Experimental results show that our approach not only is able to significantly enhance the temporal consistency of estimated depth maps over existing single-frame-based approaches, but also improves the depth estimation accuracy in terms of various evaluation metrics.

Similar Papers
  • Peer Review Report

Decision letter: Graphical-model framework for automated annotation of cell identities in dense cellular images

  • Aug 24, 2020
  • Ronald L Calabrese
  • Dissertation

A Study on Human Face Expressions using Convolutional Neural Networks and Generative Adversarial Networks

  • Jan 01, 2022
  • Sriramm Muthyala Sudhakar
  • Abstract

PATH-13. LEARNED RESIZING WITH EFFICIENT TRAINING (LRET) FACILITATES IMPROVED PERFORMANCE OF LARGE-SCALE BRAIN TUMOR HISTOLOGY IMAGE CLASSIFICATION MODELS

  • Jun 18, 2024
  • Neuro-Oncology
  • Brent A Orr +2
  • Conference Article
  • Citations2

Fast video super resolution using deep convolutional networks

  • Mar 01, 2017
  • K Chaitanya Pavan Tanay +3
  • Research Article
  • Citations15

Video Classification via Weakly Supervised Sequence Modeling

  • Nov 10, 2015
  • Computer Vision and Image Understanding
  • Jingjing Liu +4
  • Research Article
  • Citations3

The application effect of the Rasch measurement model combined with the CRF model: An analysis based on English discourse.

  • Aug 22, 2024
  • PloS one
  • Yunxia Wang
  • Conference Article

Deep Convolutional Neural Network (DCNN) Models for Accurate Analysis and Labeling of Complex Reservoir Temporal Data Sequences

  • Nov 03, 2025
  • Halah F Al-Abdulkarem +2
  • Conference Article
  • Citations167

Gaussian Conditional Random Field Network for Semantic Segmentation

  • Jun 01, 2016
  • Raviteja Vemulapalli +3
  • Conference Article
  • Citations4

Comprehensive Study of Multiple CNNs Fusion for Fine-Grained Dog Breed Categorization

  • Dec 01, 2018
  • Minori Uno +2
  • Research Article
  • Citations1

Abstract 1394: Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images from clinical ultrasound exams

  • Jul 01, 2019
  • Cancer Research
  • Xiangchun Li +22
  • Research Article
  • Citations42

DIAT-μ RadHAR (Micro-Doppler Signature Dataset) & μ RadNet (A Lightweight DCNN)—For Human Suspicious Activity Recognition

  • Apr 01, 2022
  • IEEE Sensors Journal
  • Mainak Chakraborty +3
  • Research Article
  • Citations20

Comprehensive Word-Level Classification of Screening Mammography Reports Using a Neural Network Sequence Labeling Approach.

  • Oct 18, 2018
  • Journal of Digital Imaging
  • Ryan G Short +3
  • Research Article
  • Citations2

Parkinson's disease detection and stage classification: quantitative gait evaluation through variational mode decomposition and DCNN architecture

  • Aug 09, 2024
  • Connection Science
  • Balaji E +4
  • Research Article
  • Citations15

An improved deep convolutional neural network architecture for chromosome abnormality detection using hybrid optimization model.

  • Jun 16, 2022
  • Microscopy Research and Technique
  • N Nimitha +2
  • PDF
  • Supplementary Content
  • Citations5

Application Value of a Deep Convolutional Neural Network Model for Cytological Assessment of Thyroid Nodules.

  • Nov 09, 2021
  • Journal of Healthcare Engineering
  • Ying Ren +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.