SOTAVerified

Road Segmentation

Road Segmentation is a pixel wise binary classification in order to extract underlying road network. Various Heuristic and data driven models are proposed. Continuity and robustness still remains one of the major challenges in the area.

Papers

Showing 6170 of 82 papers

TitleStatusHype
Self-Supervised Relative Depth Learning for Urban Scene Understanding0
Solving Learn-to-Race Autonomous Racing Challenge by Planning in Latent Space0
Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Boosting Off-Road Segmentation via Photometric Distortion and Exponential Moving Average0
TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation0
UdeerLID+: Integrating LiDAR, Image, and Relative Depth with Semi-Supervised0
VecRoad: Point-Based Iterative Graph Exploration for Road Graphs Extraction0
Visual Traffic Knowledge Graph Generation from Scene Images0
PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise BinarizationCode0
Semantic Binary Segmentation using Convolutional Networks without DecodersCode0
D-LinkNet: LinkNet with Pretrained Encoder and Dilated Convolution for High Resolution Satellite Imagery Road ExtractionCode0
Show:102550
← PrevPage 7 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1U-Net (ResNet-18)DWR46.5Unverified
2DeepLabV3+ (ResNet-18)DWR46.1Unverified
3U-Net (ResNet-50)DWR45.7Unverified
4FCNDWR10.7Unverified
#ModelMetricClaimedVerifiedStatus
1CoANet + PRNmIoU70.6Unverified
2SPIN Road Mapper (ours)APLS0.74Unverified
3D-LinkNetIoU0.64Unverified
#ModelMetricClaimedVerifiedStatus
1RSM-SSIoU67.35Unverified
2SPIN Road Mapper (ours)IoU65.24Unverified