.png){kind=icon}
返回
Unsupervised deep learning for depth estimation with offset pixels
.png){kind=icon}
OA
AI
DOI：10.1364/OE.385328.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Offset Pixel Aperture (OPA) camera has been recently proposed to estimate disparity of a scene with a single shot. Disparity is obtained in the image by offsetting the pixels by a fixed distance. Previously, correspondence matching schemes have been used for disparity estimation with OPA. To improve disparity estimation we use a data-oriented approach. Specifically, we use unsupervised deep learning to estimate the disparity in OPA images. We propose a simple modification to the training strategy which solves the vanishing gradients problem with the very small baseline of the OPA camera. Training degenerates to poor disparity maps if the OPA images are used directly for left-right consistency check. By using images obtained from displaced cameras at training, accurate disparity maps are obtained. The performance of the OPA camera is significantly improved compared to previously proposed single-shot cameras and unsupervised disparity estimation methods. The approach provides 8 frames per second on a single Nvidia 1080 GPU with 1024x512 OPA images. Unlike conventional approaches, which are evaluated in controlled environments, our paper shows the utility of deep learning for disparity estimation with real life sensors and low quality images. By combining OPA with deep learning, we obtain a small depth sensor capable of providing accurate disparity at usable frame rates. Also the ideas in this work can be used in small-baseline stereo systems for short-range depth estimation and multi-baseline stereo to increase the depth range. (C) 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
Keyword:
APERTURE
EXTRACTION
ACCURATE
SHAPE
期刊
IF:
3.3
论文数:
6.1W
被引数:
16.2W
机构
暂无机构信息
引用论文
The Influence of Deforestation on Land Surface Temperature—A Case Study of Perak and Kedah, Malaysia.png)
Forests
OAAI
ForestsIF0
OAAI分享收藏分享收藏分享收藏Analysis of Disparity Information for Depth Extraction Using CMOS Image Sensor with Offset Pixel Aperture Technique基于偏移像素孔径技术的CMOS图像传感器深度提取视差信息分析SENSORSOAAI
SENSORSIF3.5
OAAI分享收藏Intensity guided cost metric for fast stereo matching under radiometric variationsOPTICS EXPRESSOAAI
OPTICS EXPRESSIF3.3
OAAI分享收藏Effects of Offset Pixel Aperture Width on the Performances of Monochrome CMOS Image Sensors for Depth Extraction偏移像素孔径宽度对单色CMOS图像传感器深度提取性能的影响SENSORSOAAI
SENSORSIF3.5
OAAI分享收藏
查看更多内容