基于光场图像的深度估计及快速三维重建研究
摘要
精确性和速度取决于场景深度信息的估计。随着光场成像技术的发展,光场图像的获取越来越便利,光场图像包含
四维信息,有利于场景深度信息的精确估计。深度学习在光场图像深度估计中的应用提高了光场图像深度估计的速
度和精度,进一步能够实现场景的三维重建。本文研究利用光场图像结合深度学习进行场景深度估计,最终实现近
景快速的三维重建。
关键词
全文:
PDF参考
[1] Luo Y , Zhou W , Fang J , et al. EPI-Patch Based
Convolutional Neural Network for Depth Estimation on 4D Light
Field[C]// International Conference on Neural Information
Processing. Springer, Cham, 2017.
[2] Shin C , Jeon H G , Yoon Y , et al. EPINET: A
Fully-Convolutional Neural Network Using Epipolar Geometry
for Depth from Light Field Images[J]. IEEE, 2018.
[3] Zhou W , Wei X , Yan Y , et al. A hybrid learning
of multimodal cues for light field depth estimation[J]. Digital
Signal Processing, 2019, 95(11):102585.
[4] Tsai Y J , Liu Y L , Ming O , et al. AttentionBased View Selection Networks for Light-Field Disparity
Estimation[J]. Proceedings of the AAAI Conference on
Artificial Intelligence, 2020, 34(7):12095-12103.
[5] Woo S , Park J , Lee J Y , et al. CBAM: Convolutional
Block Attention Module[J]. Springer, Cham, 2018.
[6] Wanner S,Meister S,Goldluecke B.Datasets
and benchmarks for densely sampled 4d light field[C]//
VMV.2013:225-226.
[7] Honauer K , Johannsen O , Kondermann D , et al. A
Dataset and Evaluation Methodology for Depth Estimation on
4D Light Fields[C]// Asian Conference on Computer Vision.
Springer, Cham, 2016.
DOI: http://dx.doi.org/10.12361/2661-3727-04-02-84930
Refbacks
- 当前没有refback。