Papers › Incorporating Luminance, Depth and Color Information by a Fusion-based Network for...

Incorporating Luminance, Depth and Color Information by a Fusion-based Network for Semantic Segmentation

24 Sep 2018arXiv:1809.09077archive 2025-07-28

Shang-Wei Hung, Shao-Yuan Lo, Hsueh-Ming Hang

Semantic segmentation has made encouraging progress due to the success of deep convolutional networks in recent years. Meanwhile, depth sensors become prevalent nowadays, so depth maps can be acquired more easily. However, there are few studies that focus on the RGB-D semantic segmentation task. Exploiting the depth information effectiveness to improve performance is a challenge. In this paper, we propose a novel solution named LDFNet, which incorporates Luminance, Depth and Color information by a fusion-based network. It includes a sub-network to process depth maps and employs luminance images to assist the depth information in processes. LDFNet outperforms the other state-of-art systems on the Cityscapes dataset, and its inference speed is faster than most of the existing networks. The experimental results show the effectiveness of the proposed multi-modal fusion network and its potential for practical applications.

PaperPDFCode

Code

shangweihung/LDFNet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous DrivingReal-Time Semantic SegmentationScene UnderstandingSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation Cityscapes test LDFNet Frame (fps) 18.4 (1080Ti) #28 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes test LDFNet mIoU 71.3% #28 of 39 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val LDFNet mIoU 68.48% #23 of 24 Archive leaderboard report
Semantic Segmentation Cityscapes test LDFNet Mean IoU (class) 71.3 #76 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val LDFNet mIoU 68.48% #89 of 99 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections