Consumer Depth Cameras and Applications

Lee, Seungkyu

doi:10.1002/9781118583593.ch1

Cited by 1 publication

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While active depth sensors such as the Microsoft Kinect 1 , the Asus XTion 2 and the Intel Realsense 3 are widely available and provide accurate dense depth maps, none of them provide reliable depth information for transparent objects [15]. Structured light ones tend to provide no depth at all, while active stereo can recover a few points on the edges.…”

Section: Depth Estimationmentioning

confidence: 99%

See 1 more Smart Citation

Challenges of Depth Estimation for Transparent Objects

Weibel,

Thalhammer,

Vincze

2024

Preprint

View full text Add to dashboard Cite

Transparent objects and surfaces are pervasive in man-made environments and need to be considered in any vision system. Accurate depth data is a key factor for the reliability of such systems, requiring methods tailored for transparency to overcome the sensing shortcomings. However, the current state-of-the-art methods to predict the depth of such objects are not yet reliable enough to ensure safe operation of autonomous systems in arbitrary complex environments. In order to better understand and improve upon existing solutions, we evaluate the performance of a variety of depth estimation methods. Doing so, we disentangle the different factors impacting their performance. Among our findings, neural radiance fields offer the best accuracy, but are very sensitive to the number of images used to understand the scene, and do not benefit from any level of object understanding to help them fill in the gaps.

show abstract

Section: Depth Estimationmentioning

confidence: 99%

“…While widely available depth sensors have provided a solid baseline to recover the scene's geometry, they assume surfaces to be Lambertian [15]. Recovering the shape of transparent objects is therefore still an open challenge.…”

Section: Introductionmentioning

confidence: 99%