AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation

Daichao Zhao, Qiupu Chen, Feng He, Xin Ning, Qiankun Li

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add HG-Lane generated adverse-weather data (same total size)CLRNet ResNet-18 · HG-Lane benchmark (CLRNet ResNet-18)F1@50: 68.89 -> 88.49Improved
add HG-Lane generated dataCLRNet ResNet-18 · HG-Lane benchmark (CLRNet ResNet-18)mF1: 45.42 -> 63.03Improved
add HG-Lane generated dataCLRNet ResNet-18 · HG-Lane benchmark (CLRNet ResNet-18)F1@50 snow: 51.79 -> 84.88Improved
scale normal-only training set from 4k to 4k*6CLRNet ResNet-18 · HG-Lane benchmark (CLRNet ResNet-18)F1@50: 68.74 -> 68.89No clear effect
add lane-label mask to the Canny control map (ablation)HG-Lane · HG-Lane ablation (CLRNet ResNet-18)F1@50: 86.81 -> 88.49Improved
apply Canny before iP2P instead of the reverse order (ablation)HG-Lane · HG-Lane ablation (CLRNet ResNet-18)F1@50: 62.56 -> 88.49Improved
add Canny stage to iP2P-only generation (ablation)HG-Lane · HG-Lane ablation (CLRNet ResNet-18)F1@50: 59.75 -> 88.49Improved
add iP2P stage to Canny-only generation (ablation)HG-Lane · HG-Lane ablation (CLRNet ResNet-18)F1@50: 64.01 -> 88.49Improved
use HG-Lane instead of CycleGAN for generationCLRNet ResNet-18 · Generation quality comparison (CLRNet ResNet-18 F1@50 and FID)FID: 99.8 -> 80.1Improved
use HG-Lane instead of Stable Diffusion for generationCLRNet ResNet-18 · Generation quality comparison (CLRNet ResNet-18 F1@50 and FID)F1@50: 69.02 -> 88.49Improved
train on HG-Lane data instead of CULaneCLRNet ResNet-18 · Real-world test (CLRNet ResNet-18)F1@50: 53.03 -> 68.54Improved
train on HG-Lane data instead of CULaneCLRNet ResNet-18 · Real-world nightF1@50: 22.47 -> 60.02Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy