Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks

@inproceedings{Xie2016Deep3DFA,
  title={Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks},
  author={Junyuan Xie and Ross B. Girshick and Ali Farhadi},
  booktitle={ECCV},
  year={2016}
}
As 3D movie viewing becomes mainstream and the Virtual Reality (VR) market emerges, the demand for 3D contents is growing rapidly. Producing 3D videos, however, remains challenging. In this paper we propose to use deep neural networks to automatically convert 2D videos and images to a stereoscopic 3D format. In contrast to previous automatic 2D-to-3D conversion algorithms, which have separate stages and need ground truth depth map as supervision, our approach is trained end-to-end directly on… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 156 CITATIONS, ESTIMATED 92% COVERAGE

Deep learning based RGB-D vision tasks

VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

2D-to-Stereo Panorama Conversion Using GAN and Concentric Mosaics

VIEW 10 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

A Lightweight Neural Network for Monocular View Generation with Occlusion Handling.

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Deep 3D-Zoom Net: Unsupervised Learning of Photo-Realistic 3D-Zoom

VIEW 7 EXCERPTS
CITES BACKGROUND, RESULTS & METHODS
HIGHLY INFLUENCED

Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledge

VIEW 5 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Indirect 3D reconstruction through appearance prediction

VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Learning Monocular Depth Estimation with Unsupervised Trinocular Assumptions

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Monocular Depth Estimation with Augmented Ordinal Depth Relationships

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Single View Stereo Matching

VIEW 6 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2020

CITATION STATISTICS

  • 24 Highly Influenced Citations

  • Averaged 50 Citations per year from 2017 through 2019

  • 28% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

Conditional Random Fields as Recurrent Neural Networks

VIEW 1 EXCERPT

Deep Stereo: Learning to Predict New Views from the World's Imagery

VIEW 1 EXCERPT

End-to-End Training of Deep Visuomotor Policies

VIEW 1 EXCERPT

FlowNet: Learning Optical Flow with Convolutional Networks

VIEW 2 EXCERPTS