A Discussion on Variants of an Anisotropic Model Applied to Depth Completion
Communications in Computer and Information Science, ISSN: 1865-0937, Vol: 1937 CCIS, Page: 3-16
2024
- 1Citations
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Metrics Details
- Citations1
- Citation Indexes1
Conference Paper Description
Depth data holds significant importance in numerous applications, ranging from video games to autonomous vehicles. Depth data can be acquired by sensors such as LiDAR sensors. Frequently, acquired depth map has holes or data that presents low confidence level. The task of depth data interpolation or completion stands as a fundamental requirement for such applications. Infinity Laplacian is an interpolator of data that can perform this task. The Infinity Laplacian represents the most straightforward interpolator, adhering to a set of appropriate axioms. In this study, we assessed three different variations of the infinity Laplacian for the purpose of completing sparse depth data. We sub-sampled the publicly available NUY_V2 dataset and evaluated the performance of these models by up-sampling depth data. In this paper, we compared the infinity Laplacian, unbalanced infinity Laplacian, balanced infinity Laplacian, and biased infinity Laplacian. Obtained results show that the balanced infinity Laplacian outperforms the other three models and also many contemporaneous models. The addition of a mechanism that balances between two eikonal operators gives the infinity the capability to reach better performance in the up-sampling task. Moving forward, our focus will be directed towards addressing the challenge of edge interpolation using the color reference image.
Bibliographic Details
http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85180749538&origin=inward; http://dx.doi.org/10.1007/978-3-031-48930-3_1; https://link.springer.com/10.1007/978-3-031-48930-3_1; https://dx.doi.org/10.1007/978-3-031-48930-3_1; https://link.springer.com/chapter/10.1007/978-3-031-48930-3_1
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know