Method Details

Details for method 'LDFNet'

name	LDFNet
challenge	pixel-level semantic labeling
details	We propose a preferred solution, which incorporates Luminance, Depth and color information by a Fusion-based network named LDFNet. It includes a distinctive encoder sub-network to process the depth maps and further employs the luminance images to assist the depth information in a process. LDFNet achieves very competitive results compared to the other state-of-art systems on the challenging Cityscapes dataset, while it maintains an inference speed faster than most of the existing top-performing networks. The experimental results show the effectiveness of the proposed information-fused approach and the potential of LDFNet for road scene understanding tasks.
publication	Incorporating Luminance, Depth and Color Information by Fusion-based Networks for Semantic Segmentation Shang-Wei Hung, Shao-Yuan Lo https://arxiv.org/abs/1809.09077
project page / code	https://github.com/shangweihung/LDFNet
used Cityscapes data	fine annotations, stereo
used external data
runtime	n/a
subsampling	2
submission date	September, 2018
previous submissions