Cover Image

LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zijie, Zhang, Weiming, Zhang, Wei, Tan, Xiao, Liu, Hongxing, Wang, Yaowei, Li, Guanbin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

World Models as Group Actions
by: Wang, Zijie, et al.
Published: (2026)

OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives
by: Dan, Zedong, et al.
Published: (2026)

TS-CGNet: Temporal-Spatial Fusion Meets Centerline-Guided Diffusion for BEV Mapping
by: Hong, Xinying, et al.
Published: (2025)

BEV$^2$PR: BEV-Enhanced Visual Place Recognition with Structural Cues
by: Ge, Fudong, et al.
Published: (2024)

Lane Graph Extraction from Aerial Imagery via Lane Segmentation Refinement with Diffusion Models
by: Ruiz, Antonio, et al.
Published: (2024)

HeightLane: BEV Heightmap guided 3D Lane Detection
by: Park, Chaesong, et al.
Published: (2024)

DeformCL: Learning Deformable Centerline Representation for Vessel Extraction in 3D Medical Image
by: Zhao, Ziwei, et al.
Published: (2025)

DB3D-L: Depth-aware BEV Feature Transformation for Accurate 3D Lane Detection
by: Liu, Yehao, et al.
Published: (2025)

GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection
by: Song, Ziying, et al.
Published: (2024)

Circle of Willis Centerline Graphs: A Dataset and Baseline Algorithm
by: Musio, Fabio, et al.
Published: (2025)

Deeply-Conditioned Image Compression via Self-Generated Priors
by: Zhao, Zhineng, et al.
Published: (2025)

Dynamic Exploration on Segment-Proposal Graphs for Tubular Centerline Tracking
by: Di, Chong, et al.
Published: (2025)

MaskBEV: Towards A Unified Framework for BEV Detection and Map Segmentation
by: Zhao, Xiao, et al.
Published: (2024)

Lane Departure Accident Prevention in Foggy Conditions: A Prior-Guided Dynamic Feature Fusion Transformer Framework for Real-Time Lane Detection
by: Zhang, Ronghui, et al.
Published: (2025)

GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection
by: Zhang, Jinqing, et al.
Published: (2024)

LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating
by: Xia, Deguo, et al.
Published: (2025)

BLOS-BEV: Navigation Map Enhanced Lane Segmentation Network, Beyond Line of Sight
by: Wu, Hang, et al.
Published: (2024)

Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors
by: Li, Han, et al.
Published: (2024)

UniFL: Improve Latent Diffusion Model via Unified Feedback Learning
by: Zhang, Jiacheng, et al.
Published: (2024)

MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction
by: Hao, Xiaoshuai, et al.
Published: (2025)

LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement
by: Peng, Renyuan, et al.
Published: (2024)

Improving Deep Representation Learning via Auxiliary Learnable Target Coding
by: Liu, Kangjun, et al.
Published: (2023)

DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
by: Huang, Junjia, et al.
Published: (2026)

DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior
by: Zhang, Yiming, et al.
Published: (2024)

PR-DETR: Injecting Position and Relation Prior for Dense Video Captioning
by: Li, Yizhe, et al.
Published: (2025)

DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation
by: Xia, Deguo, et al.
Published: (2024)

Towards Real-World Blind Face Restoration with Generative Diffusion Prior
by: Chen, Xiaoxu, et al.
Published: (2023)

Depth3DLane: Monocular 3D Lane Detection via Depth Prior Distillation
by: Lyu, Dongxin, et al.
Published: (2025)

VesselFusion: Diffusion Models for Vessel Centerline Extraction from 3D CT Images
by: Mita, Soichi, et al.
Published: (2026)

TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior
by: Yang, Sen, et al.
Published: (2024)

Centerline Boundary Dice Loss for Vascular Segmentation
by: Shi, Pengcheng, et al.
Published: (2024)

DiffusionLane: Diffusion Model for Lane Detection
by: Zhou, Kunyang, et al.
Published: (2025)

InstanceBEV: Unifying Instance and BEV Representation for 3D Panoptic Segmentation
by: Li, Feng, et al.
Published: (2025)

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
by: Liao, Bencheng, et al.
Published: (2023)

BEVWorld: A Multimodal World Simulator for Autonomous Driving via Scene-Level BEV Latents
by: Zhang, Yumeng, et al.
Published: (2024)

DreamLayer: Simultaneous Multi-Layer Generation via Diffusion Mode
by: Huang, Junjia, et al.
Published: (2025)

TempBEV: Improving Learned BEV Encoders with Combined Image and BEV Space Temporal Aggregation
by: Monninger, Thomas, et al.
Published: (2024)

Noise-Injected Spiking Graph Convolution for Energy-Efficient 3D Point Cloud Denoising
by: Li, Zikuan, et al.
Published: (2025)

ChatBEV: A Visual Language Model that Understands BEV Maps
by: Xu, Qingyao, et al.
Published: (2025)

Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models
by: Yang, Zeyu, et al.
Published: (2024)