SemanticPaint

Golodetz, Stuart; Sapienza, Michael; Valentin, Julien; Vineet, Vibhav; Cheng, Ming–Ming; Prisacariu, Victor Adrian; Kähler, Olaf; Ren, Carl Yuheng; Arnab, Anurag; Hicks, Stephen L.; Murray, David; Izadi, Shahram; Torr, Philip H. S.

doi:10.1145/2775280.2792589

Cited by 12 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few decades, many methods are proposed [1][2][3][4][5][6] for solving the problem, but those methods are unable to tackle all the scene, especially the extreme conditions. Recently, the approaches based on convolutional neural networks (CNNs) have been developed to perform camera relocalization due to their adaptive capabilities to illumination change and motion blur.…”

Section: Introductionmentioning

confidence: 99%

Euler Angles Based Loss Function for Camera Localization with Deep Learning

Fang

Zhao

Tang

et al. 2018

2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER)

View full text Add to dashboard Cite

Deep learning has been applied to camera relocalization, in particular, PoseNet and its extended work are the convolutional neural networks which regress the camera pose from a single image. However there are many problems, one of them is expensive parameter selection.In this paper, we directly explore the three Euler angles as the orientation representation in the camera pose regressor. There is no need to select the parameter, which is not tolerant in the previous works. Experimental results on the 7 Scenes datasets and the King's College dataset demonstrate that it has competitive performances.

show abstract