Journal
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Volume -, Issue -, Pages 12438-12447Publisher
IEEE
DOI: 10.1109/CVPR.2019.01273
Keywords
-
Funding
- Changan US
Ask authors/readers for more resources
Depth completion involves estimating a dense depth image from sparse depth measurements, often guided by a color image. While linear upsampling is straight forward, it results in depth pixels being interpolated in empty space across discontinuities between objects. Current methods use deep networks to maintain gaps between objects. Nevertheless depth smearing remains a challenge. We propose a new representation for depth called Depth Coefficients (DC) to address this problem. It enables convolutions to more easily avoid inter-object depth mixing. We also show that the standard Mean Squared Error (MSE) loss function can promote depth mixing, and so we propose instead to use cross-entropy loss for DC. Both quantitative and qualitative evaluation are conducted on benchmarks, and we show that switching out sparse depth input and MSE loss functions with our DC representation and loss is a simple way to improve performance, reduce pixel depth mixing and can improve object detection.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available