Pith. sign in

REVIEW 2 major objections 2 minor 35 references

A hierarchical centerline representation creates cyclic interaction between detection and topology reasoning to improve lane understanding in driving scenes.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-07-01 08:55 UTC pith:TTXTPDR7

load-bearing objection TopoHR layers point/instance/semantic queries into a cyclic decoder with explicit P2I links, but the large OpenLane-V2 deltas need controlled re-runs of baselines to be convincing. the 2 major comments →

arxiv 2604.24119 v2 pith:TTXTPDR7 submitted 2026-04-27 cs.CV

TopoHR: Hierarchical Centerline Representation for Cyclic Topology Reasoning in Driving Scenes with Point-to-Instance Relations

Yifeng Bai , Zhirong Chen , Bo Song , Erkang Cheng , Haibin Ling This is my paper
classification cs.CV
keywords topology reasoningcenterline detectionhierarchical representationpoint-to-instance relationsautonomous drivinglane topologyOpenLane-V2
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper seeks to overcome limitations in existing centerline detection methods that treat topology reasoning as a separate sequential step and overlook point-to-instance relationships. It introduces TopoHR as an end-to-end framework where point queries, instance queries, and semantic representations interact cyclically through a shared decoder and unified reasoning module. This setup lets fine-grained point-level details and global instance connections refine each other iteratively. A sympathetic reader would care because better topology reasoning directly supports safer autonomous driving by producing more accurate lane graphs from sensor data. The reported benchmark gains on OpenLane-V2 serve as evidence that the cyclic mechanism delivers measurable improvements over prior approaches.

Core claim

TopoHR establishes cyclic interaction between centerline detection and topology reasoning by introducing a hierarchical centerline representation of point queries, instance queries, and semantic representations that are fused inside a hierarchical decoder, together with a topology reasoning module that jointly models point-to-instance relations and instance-to-instance connections inside one architecture.

What carries the argument

Hierarchical centerline representation consisting of point queries, instance queries, and semantic representations that are integrated and fused inside a hierarchical decoder, enabling cyclic mutual enhancement with a topology reasoning module that captures both P2I and I2I relations.

Load-bearing premise

That the cyclic interaction produced by fusing point, instance, and semantic queries will generate the claimed performance gains on the chosen OpenLane-V2 subsets without any changes to evaluation protocols.

What would settle it

Running TopoHR on OpenLane-V2 subset A or B and finding no improvement, or smaller gains than +3.8 DET_l and +5.4 TOP_ll on A or +11.0 DET_l and +7.9 TOP_ll on B, over the previous best results.

Watch this falsifier — get emailed when new claim-graph text bears on it.

If this is right

  • More accurate centerline detection measured by DET_l on both OpenLane-V2 subsets.
  • Stronger topology reasoning measured by TOP_ll on both subsets.
  • End-to-end training replaces separate sequential MLP-based topology modules.
  • Explicit modeling of point-to-instance relations alongside instance-to-instance connections inside one module.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same query hierarchy might be tested on other multi-scale perception tasks such as object detection with part-whole relations.
  • Public code release would let others check whether the cyclic mechanism transfers to datasets beyond OpenLane-V2.
  • The approach could reduce reliance on post-processing steps that current pipelines use to enforce topology consistency.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

2 major / 2 minor

Summary. The manuscript presents TopoHR, an end-to-end framework for topology reasoning in driving scenes. It proposes a hierarchical centerline representation using point queries, instance queries, and semantic representations integrated in a hierarchical decoder, along with a hierarchical topology reasoning module that captures point-to-instance (P2I) and instance-to-instance (I2I) relations. The method establishes cyclic interaction between centerline detection and topology reasoning. On the OpenLane-V2 benchmark, it reports state-of-the-art performance with improvements of +3.8 in DET_l and +5.4 in TOP_ll on subset_A, and +11.0 in DET_l and +7.9 in TOP_ll on subset_B compared to previous best results.

Significance. If the performance gains are attributable to the proposed hierarchical cyclic design rather than evaluation differences, this work could advance autonomous driving perception by demonstrating the benefits of multi-level feature integration and iterative enhancement between detection and reasoning tasks. The commitment to public code release is a positive aspect for reproducibility.

major comments (2)
  1. [Abstract and Experiments] Abstract and Experiments: The central performance claims rely on comparisons to 'previous best results' on OpenLane-V2. However, it is not clear whether the baseline methods were re-evaluated using the same data splits, preprocessing, augmentation, training schedules, and metric implementations as TopoHR. Without such controlled comparisons, the reported deltas cannot be confidently attributed to the hierarchical P2I/I2I modules.
  2. [Experiments] Experiments section: The manuscript reports benchmark numbers but the provided description lacks explicit ablation tables, error bars, or dataset-split details that would verify the contribution of the cyclic interaction and hierarchical queries to the claimed gains.
minor comments (2)
  1. [Abstract] The notation for metrics (DET_l, TOP_ll) and subsets (subset_A, subset_B) should be explicitly defined or referenced to the OpenLane-V2 paper for clarity.
  2. Ensure figure captions and method diagrams clearly distinguish the point-to-instance relations from instance-to-instance connections.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback. We address the two major comments point-by-point below. Where revisions are warranted we indicate them explicitly and will incorporate the changes in the next version of the manuscript.

read point-by-point responses

  1. Referee: [Abstract and Experiments] The central performance claims rely on comparisons to 'previous best results' on OpenLane-V2. However, it is not clear whether the baseline methods were re-evaluated using the same data splits, preprocessing, augmentation, training schedules, and metric implementations as TopoHR. Without such controlled comparisons, the reported deltas cannot be confidently attributed to the hierarchical P2I/I2I modules.

    Authors: We followed the official OpenLane-V2 benchmark protocol and reported the numbers exactly as published in the original baseline papers, which remains the prevailing practice for this benchmark. All methods share the same official data splits and metric definitions. To strengthen the manuscript we will add an explicit paragraph in the Experiments section clarifying the evaluation protocol and confirming that no custom preprocessing or metric alterations were introduced for TopoHR. While a full re-implementation of every baseline under identical training schedules would be desirable, the ablation studies already isolate the contribution of the hierarchical P2I/I2I modules under controlled conditions within our own framework. revision: partial

  2. Referee: [Experiments] The manuscript reports benchmark numbers but the provided description lacks explicit ablation tables, error bars, or dataset-split details that would verify the contribution of the cyclic interaction and hierarchical queries to the claimed gains.

    Authors: Section 4.3 already contains ablation tables that quantify the incremental gains from the point queries, instance queries, semantic representations, and the unified P2I+I2I topology module. We will revise this section to (i) present the ablations in a single consolidated table, (ii) report standard deviations over three independent runs as error bars, and (iii) restate the exact train/val/test splits used for both subsets. These additions will make the contribution of the cyclic interaction and hierarchical design more transparent. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical architecture paper with independent benchmark evaluation

full rationale

The paper presents an end-to-end neural architecture (hierarchical queries, P2I/I2I modules, cyclic interaction) for centerline detection and topology reasoning. It reports empirical gains on OpenLane-V2 without any first-principles derivation, fitted-parameter predictions, or self-referential equations. No load-bearing self-citations, uniqueness theorems, or ansatzes are invoked in the provided text. The central claims rest on standard benchmark deltas rather than any reduction of outputs to inputs by construction. This is the normal case of a self-contained empirical CV method.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review supplies no explicit free parameters, axioms, or invented entities; the performance claim rests on the unstated assumption that the OpenLane-V2 evaluation protocol and splits are fixed and that the reported metric improvements are not the result of hyperparameter search on the test set.

pith-pipeline@v0.9.1-grok · 5837 in / 1143 out tokens · 18049 ms · 2026-07-01T08:55:28.762064+00:00 · methodology

0 comments
read the original abstract

Topology reasoning is crucial for autonomous driving. Current methods primarily focus on instance-level learning for centerline detection, followed by a sequential module for topology reasoning that relies on simplified MLP layers. Moreover, they often neglect the importance of \textit{point-to-instance} (P2I) relationships in topology reasoning. To address these limitations, we present TopoHR (Topological Hierarchical Representation), a novel end-to-end framework that establishes cyclic interaction between centerline detection and topology reasoning, allowing them to iteratively enhance each other. Specifically, we introduce a hierarchical centerline representation including point queries, instance queries, and semantic representations. These multi-level features are seamlessly integrated and fused within a hierarchical centerline decoder. Furthermore, we design a hierarchical topology reasoning module that captures both fine-grained P2I relationships and global instance-to-instance (I2I) connections within a unified architecture. With these novel components, TopoHR ensures accurate and robust topology reasoning. On the OpenLane-V2 benchmark, TopoHR refreshes state-of-the-art performance with significant improvements. Notably, compared with previous best results, TopoHR achieves +3.8 in $\mathrm{DET}_{\text{l}}$, +5.4 in $\mathrm{TOP}_{\text{ll}}$ on $\text{subset_A}$ and +11.0 in $\mathrm{DET}_{\text{l}}$, +7.9 in $\mathrm{TOP}_{\text{ll}}$ on $\text{subset_B}$, validating the effectiveness of the proposed components. The code will be shared publicly at https://github.com/Yifeng-Bai/TopoHR.git.

Figures

Figures reproduced from arXiv: 2604.24119 by Bo Song, Erkang Cheng, Haibin Ling, Yifeng Bai, Zhirong Chen.

Figure 1
Figure 1. Figure 1: Different centerline detection and topology reasoning view at source ↗
Figure 2
Figure 2. Figure 2: Overview of TopoHR. Aside from a BEV feature extractor and a traffic element decoder, TopoHR has three notable compo view at source ↗
Figure 3
Figure 3. Figure 3: Illustration of the detailed architecture of hierarchical decoder Layer and hierarchical topology module: (a) an Instance-Aware view at source ↗
Figure 4
Figure 4. Figure 4: Instance-to-instance and point-to-instance topology rea view at source ↗
Figure 5
Figure 5. Figure 5: More instance-to-instance and point-to-instance topology reasoning results. (a) Groundtruth of centerline topology reasoning, view at source ↗
Figure 6
Figure 6. Figure 6: Illustration of detection and topology reasoning results on OpenLane-V2 validation dataset. view at source ↗
Figure 7
Figure 7. Figure 7: More qualitative results. With our proposed designs, TopoHR achieves more accurate reasoning of both centerline-to-centerline view at source ↗

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

35 extracted references · 7 canonical work pages · 2 internal anchors

  1. [1]

    nuscenes: A multi- modal dataset for autonomous driving

    Holger Caesar, Varun Bankiti, Alex H Lang, Sourabh V ora, Venice Erin Liong, Qiang Xu, Anush Krishnan, Yu Pan, Gi- ancarlo Baldan, and Oscar Beijbom. nuscenes: A multi- modal dataset for autonomous driving. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 11621–11631, 2020. 6

    2020

  2. [2]

    Structured bird’s-eye-view traffic scene un- derstanding from onboard images

    Yigit Baran Can, Alexander Liniger, Danda Pani Paudel, and Luc Van Gool. Structured bird’s-eye-view traffic scene un- derstanding from onboard images. In2021 IEEE/CVF In- ternational Conference on Computer Vision (ICCV), pages 15641–15650. IEEE Computer Society, 2021. 3

    2021

  3. [3]

    Masked-attention mask transformer for universal image segmentation

    Bowen Cheng, Ishan Misra, Alexander G Schwing, Alexan- der Kirillov, and Rohit Girdhar. Masked-attention mask transformer for universal image segmentation. InProceed- ings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1290–1299, 2022. 5

    2022

  4. [4]

    Mask2map: Vectorized hd map construction using bird’s eye view segmentation masks

    Sehwan Choi, Jungho Kim, Hongjae Shin, and Jun Won Choi. Mask2map: Vectorized hd map construction using bird’s eye view segmentation masks. InEuropean Confer- ence on Computer Vision, pages 19–36. Springer, 2024. 2

    2024

  5. [5]

    Piv- otnet: Vectorized pivot learning for end-to-end hd map con- struction

    Wenjie Ding, Limeng Qiao, Xi Qiu, and Chi Zhang. Piv- otnet: Vectorized pivot learning for end-to-end hd map con- struction. In2023 IEEE/CVF International Conference on Computer Vision (ICCV), pages 3649–3659. IEEE, 2023. 3

    2023

  6. [6]

    Topopoint: Enhance topology rea- soning via endpoint detection in autonomous driving

    Yanping Fu, Xinyuan Liu, Tianyu Li, Yike Ma, Yucheng Zhang, and Feng Dai. Topopoint: Enhance topology rea- soning via endpoint detection in autonomous driving. InThe Thirty-ninth Annual Conference on Neural Information Pro- cessing Systems. 7

  7. [7]

    Topologic: An in- terpretable pipeline for lane topology reasoning on driving scenes.Advances in Neural Information Processing Systems, 37:61658–61676, 2024

    Yanping Fu, Wenbin Liao, Xinyuan Liu, Hang Xu, Yike Ma, Yucheng Zhang, and Feng Dai. Topologic: An in- terpretable pipeline for lane topology reasoning on driving scenes.Advances in Neural Information Processing Systems, 37:61658–61676, 2024. 1, 2, 3, 4, 6, 7, 8

    2024

  8. [8]

    3d-lanenet: End-to-end 3d multiple lane detection

    Noa Garnett, Rafi Cohen, Tomer Pe’er, Roee Lahav, and Dan Levi. 3d-lanenet: End-to-end 3d multiple lane detection. In 2019 IEEE/CVF International Conference on Computer Vi- sion (ICCV), pages 2921–2930. IEEE, 2019. 1

    2019

  9. [9]

    Deep residual learning for image recognition

    Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. InProceed- ings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. 6

    2016

  10. [10]

    Relation detr: Exploring explicit position relation prior for object detection

    Xiuquan Hou, Meiqin Liu, Senlin Zhang, Ping Wei, Badong Chen, and Xuguang Lan. Relation detr: Exploring explicit position relation prior for object detection. InEuropean Con- ference on Computer Vision, pages 89–105. Springer, 2024. 5

    2024

  11. [11]

    Topomask: Instance-mask-based formu- lation for the road topology problem via transformer-based architecture.arXiv preprint arXiv:2306.05419, 2023

    M Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc, and Alptekin Temizel. Topomask: Instance-mask-based formu- lation for the road topology problem via transformer-based architecture.arXiv preprint arXiv:2306.05419, 2023. 1, 3

    work page arXiv 2023

  12. [12]

    Topomaskv2: Enhanced instance-mask- based formulation for the road topology problem.arXiv preprint arXiv:2409.11325, 2024

    M Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kilinc, and Alptekin Temizel. Topomaskv2: Enhanced instance-mask- based formulation for the road topology problem.arXiv preprint arXiv:2409.11325, 2024. 1, 2

    work page arXiv 2024

  13. [13]

    Topobda: Towards bezier de- formable attention for road topology understanding.Neuro- computing, page 132360, 2025

    Muhammet Esat Kalfaoglu, Halil Ibrahim Ozturk, Ozsel Kil- inc, and Alptekin Temizel. Topobda: Towards bezier de- formable attention for road topology understanding.Neuro- computing, page 132360, 2025. 1

    2025

  14. [14]

    Hdmapnet: An online hd map construction and evaluation framework

    Qi Li, Yue Wang, Yilun Wang, and Hang Zhao. Hdmapnet: An online hd map construction and evaluation framework. In 2022 International Conference on Robotics and Automation (ICRA), pages 4628–4634. IEEE, 2022. 2

    2022

  15. [15]

    Graph-based topology reasoning for driv- ing scenes.Transactions on Machine Learning Research

    Tianyu Li, Li Chen, Huijie Wang, Yang Li, Jiazhi Yang, Xiangwei Geng, Shengyin Jiang, Yuting Wang, Hang Xu, Chunjing Xu, et al. Graph-based topology reasoning for driv- ing scenes.Transactions on Machine Learning Research. 1, 2, 3, 7

  16. [16]

    Lanesegnet: Map learning with lane segment perception for autonomous driving

    Tianyu Li, Peijin Jia, Bangjun Wang, Li Chen, Kun Jiang, Junchi Yan, and Hongyang Li. Lanesegnet: Map learning with lane segment perception for autonomous driving. In 12th International Conference on Learning Representations, ICLR 2024, 2024. 1, 3

    2024

  17. [17]

    Bevformer: learning bird’s-eye-view representation from lidar-camera via spatiotemporal transformers.IEEE Transactions on Pat- tern Analysis and Machine Intelligence, 2024

    Zhiqi Li, Wenhai Wang, Hongyang Li, Enze Xie, Chong- hao Sima, Tong Lu, Qiao Yu, and Jifeng Dai. Bevformer: learning bird’s-eye-view representation from lidar-camera via spatiotemporal transformers.IEEE Transactions on Pat- tern Analysis and Machine Intelligence, 2024. 6

    2024

  18. [18]

    Maptr: Structured modeling and learning for online vectorized hd map construction

    Bencheng Liao, Shaoyu Chen, Xinggang Wang, Tianheng Cheng, Qian Zhang, Wenyu Liu, and Chang Huang. Maptr: Structured modeling and learning for online vectorized hd map construction. InThe Eleventh International Conference on Learning Representations. 1, 2

  19. [19]

    Focal loss for dense object detection.IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2):318–327, 2018

    TY Lin, P Goyal, R Girshick, K He, and P Dollar. Focal loss for dense object detection.IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2):318–327, 2018. 6

    2018

  20. [20]

    Feature pyra- mid networks for object detection

    Tsung-Yi Lin, Piotr Doll ´ar, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyra- mid networks for object detection. InProceedings of the IEEE conference on computer vision and pattern recogni- tion, pages 2117–2125, 2017. 6

    2017

  21. [21]

    Mgmap: Mask-guided learn- ing for online vectorized hd map construction

    Xiaolu Liu, Song Wang, Wentong Li, Ruizi Yang, Junbo Chen, and Jianke Zhu. Mgmap: Mask-guided learn- ing for online vectorized hd map construction. In2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14812–14821. IEEE Computer Society, 2024. 2

    2024

  22. [22]

    Vectormapnet: End-to-end vectorized hd map learning

    Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, and Hang Zhao. Vectormapnet: End-to-end vectorized hd map learning. InInternational Conference on Machine Learning, pages 22352–22369. PMLR, 2023. 2

    2023

  23. [23]

    Decoupled Weight Decay Regularization

    Ilya Loshchilov and Frank Hutter. Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017. 7

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  24. [24]

    Aug- menting lane perception and topology understanding with standard definition navigation maps

    Katie Z Luo, Xinshuo Weng, Yan Wang, Shuang Wu, Jie Li, Kilian Q Weinberger, Yue Wang, and Marco Pavone. Aug- menting lane perception and topology understanding with standard definition navigation maps. In2024 IEEE Inter- national Conference on Robotics and Automation (ICRA), pages 4029–4035. IEEE, 2024. 3, 7

    2024

  25. [25]

    Reltopo: En- hancing relational modeling for driving scene topology rea- soning.arXiv preprint arXiv:2506.13553, 2025

    Yueru Luo, Changqing Zhou, Yiming Yang, Erlong Li, Chao Zheng, Shuqi Mei, Shuguang Cui, and Zhen Li. Reltopo: En- hancing relational modeling for driving scene topology rea- soning.arXiv preprint arXiv:2506.13553, 2025. 3, 7

    work page arXiv 2025

  26. [26]

    T2sg: Traffic topology scene graph for topology reasoning in autonomous driving

    Changsheng Lv, Mengshi Qi, Liang Liu, and Huadong Ma. T2sg: Traffic topology scene graph for topology reasoning in autonomous driving. In2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 17197–17206. IEEE Computer Society, 2025. 1, 2, 3, 7

    2025

  27. [27]

    Sept: Standard-definition map enhanced scene perception and topology reasoning for au- tonomous driving.IEEE Robotics and Automation Letters,

    Muleilan Pei, Jiayao Shan, Peiliang Li, Jieqi Shi, Jing Huo, Yang Gao, and Shaojie Shen. Sept: Standard-definition map enhanced scene perception and topology reasoning for au- tonomous driving.IEEE Robotics and Automation Letters,

  28. [28]

    Openlane-v2: A topology reasoning benchmark for unified 3d hd mapping.Advances in Neural Information Processing Systems, 36, 2024

    Huijie Wang, Tianyu Li, Yang Li, Li Chen, Chonghao Sima, Zhenbo Liu, Bangjun Wang, Peijin Jia, Yuting Wang, Shengyin Jiang, et al. Openlane-v2: A topology reasoning benchmark for unified 3d hd mapping.Advances in Neural Information Processing Systems, 36, 2024. 2, 6

    2024

  29. [29]

    Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting

    Benjamin Wilson, William Qi, Tanmay Agarwal, John Lambert, Jagjeet Singh, Siddhesh Khandelwal, Bowen Pan, Ratnesh Kumar, Andrew Hartnett, Jhony Kaesemodel Pontes, et al. Argoverse 2: Next generation datasets for self-driving perception and forecasting.arXiv preprint arXiv:2301.00493, 2023. 6

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  30. [30]

    Topomlp: An simple yet strong pipeline for driving topology reasoning.arXiv preprint arXiv:2310.06753, 2023

    Dongming Wu, Jiahao Chang, Fan Jia, Yingfei Liu, Tiancai Wang, and Jianbing Shen. Topomlp: An simple yet strong pipeline for driving topology reasoning.arXiv preprint arXiv:2310.06753, 2023. 1, 2, 3

    work page arXiv 2023

  31. [31]

    Centerlinedet: Centerline graph detection for road lanes with vehicle-mounted sensors by transformer for hd map generation

    Zhenhua Xu, Yuxuan Liu, Yuxiang Sun, Ming Liu, and Lu- jia Wang. Centerlinedet: Centerline graph detection for road lanes with vehicle-mounted sensors by transformer for hd map generation. In2023 IEEE International Conference on Robotics and Automation (ICRA), pages 3553–3559. IEEE,

  32. [32]

    Toposd: Topology-enhanced lane segment perception with sdmap prior.arXiv preprint arXiv:2411.14751, 2024

    Sen Yang, Minyue Jiang, Ziwei Fan, Xiaolu Xie, Xiao Tan, Yingying Li, Errui Ding, Liang Wang, and Jingdong Wang. Toposd: Topology-enhanced lane segment perception with sdmap prior.arXiv preprint arXiv:2411.14751, 2024. 3

    work page arXiv 2024

  33. [33]

    Topo2seq: En- hanced topology reasoning via topology sequence learning

    Yiming Yang, Yueru Luo, Bingkun He, Erlong Li, Zhipeng Cao, Chao Zheng, Shuqi Mei, and Zhen Li. Topo2seq: En- hanced topology reasoning via topology sequence learning. InProceedings of the AAAI Conference on Artificial Intelli- gence, pages 9318–9326, 2025. 3

    2025

  34. [34]

    Online map vec- torization for autonomous driving: A rasterization perspec- tive.Advances in Neural Information Processing Systems, 36:31865–31877, 2023

    Gongjie Zhang, Jiahao Lin, Shuang Wu, Zhipeng Luo, Yang Xue, Shijian Lu, Zuoguan Wang, et al. Online map vec- torization for autonomous driving: A rasterization perspec- tive.Advances in Neural Information Processing Systems, 36:31865–31877, 2023. 2

    2023

  35. [35]

    TopoHR, Ins

    Yi Zhou, Hui Zhang, Jiaqian Yu, Yifan Yang, Sangil Jung, Seung-In Park, and ByungIn Yoo. Himap: Hybrid repre- sentation learning for end-to-end vectorized hd map con- struction. In2024 IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition (CVPR), pages 15396–15406. IEEE, 2024. 3 TopoHR: Hierarchical Centerline Representation for Cyclic Topology...

    2024