PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction

Bo Lang; Nirav Savaliya; Zhihao Zheng; Jinglun Feng; Zheng-Hang Yeh; Mooi Choo Chuah

cs.CVFeb 18, 2026

PredMapNet: Future and Historical Reasoning for Consistent Online HD Vectorized Map Construction

Authors: Bo Lang, Nirav Savaliya, Zhihao Zheng, Jinglun Feng, Zheng-Hang Yeh, Mooi Choo Chuah

Organizations: Lehigh University · Honda Research Institute USA

Abstract

High-definition (HD) maps are crucial to autonomous driving, providing structured representations of road elements to support navigation and planning. However, existing query-based methods often employ random query initialization and depend on implicit temporal modeling, which lead to temporal inconsistencies and instabilities during the construction of a global map. To overcome these challenges, we introduce a novel end-to-end framework for consistent online HD vectorized map construction, which jointly performs map instance tracking and short-term prediction. First, we propose a Semantic-Aware Query Generator that initializes queries with spatially aligned semantic masks to capture scene-level context globally. Next, we design a History Rasterized Map Memory to store fine-grained instance-level maps for each tracked instance, enabling explicit historical priors. A History-Map Guidance Module then integrates rasterized map information into track queries, improving temporal continuity. Finally, we propose a Short-Term Future Guidance module to forecast the immediate motion of map instances based on the stored history trajectories. These predicted future locations serve as hints for tracked instances to further avoid implausible predictions and keep temporal consistency. Extensive experiments on the nuScenes and Argoverse2 datasets demonstrate that our proposed method outperforms state-of-the-art (SOTA) methods with good efficiency.

Figures & tables

Figure 1: Comparison of several HD map construction methods: (a) Single-Frame, (b) Temporal Propagation, (c) PredMapNet (Ours) utilizes semantic-aware information and enables both historical & future reasoning for better query decoding.

Figure 2: The architecture pipeline of PredMapNet. At each frame, multi-view images are processed by a BEV encoder to extract perception features. The Semantic-Aware Query Generator 3.2 produces semantic-aware detection queries and rasterized map from BEV features. A History Rasterized Map Memory 3.3 is maintained to store instance-level segmentation masks over time. The History-Map Guidance Module 3.4 refines track queries with historical geometric priors from memory. Simultaneously, the Short-Term Future Guidance Module 3.5 predicts future polylines from historical trajectories and fuses them into track queries to guide query initialization in the next frame. Together, these modules enable temporally consistent and robust map instance construction across frames.

Method	Epoch	$AP_{ped}$	$AP_{divider}$	$AP_{boundary}$	$m$ AP $\uparrow$	C- $m$ AP $\uparrow$	FPS
PivotNet [ 9 ]	24	56.2	56.5	60.1	57.6	-	-
MapTRv2 [ 19 ]	24	59.8	62.4	62.4	61.5	41.7	14.1
HRMapNet [ 43 ]	24	65.8	67.4	68.5	67.3	49.2	10.3
StreamMapNet [ 39 ]	24	61.9	66.3	62.1	63.4	38.4	13.1
MGMap [ 22 ]	24	61.8	65.0	67.5	64.8	43.5	13.4
Mask2Map [ 8 ]	24	70.6	71.3	72.9	71.6	55.8	9.2

Table 1: Comparison with SOTA methods on the nuScenes validation set (old split [ 19 ] ).

Method	Epoch	$AP_{ped}$	$AP_{divider}$	$AP_{boundary}$	$m$ AP $\uparrow$	C- $m$ AP $\uparrow$
MapTRv2 [ 19 ]	24	62.9	72.1	67.1	67.4	-
HRMapNet [ 43 ]	30	65.1	71.4	68.6	68.3	-
StreamMapNet [ 39 ]	72	70.5	74.2	66.1	70.3	-
Mask2Map [ 8 ]	24	68.1	72.7	73.7	71.5	-
MGMapNet [ 38 ]	24	71.3	76.0	73.1	73.6	-
MapTracker [ 5 ]	35	76.9	79.9	73.6	76.8	68.3

Table 2: Comparison with SOTA methods on the Argoverse2 validation set.

Method	Epoch	$AP_{ped}^{\dagger}$	$AP_{divider}^{\dagger}$	$AP_{boundary}^{\dagger}$	$m\text{AP}^{\dagger}$
MapTR [ 18 ]	24	32.4	23.5	17.1	24.3
$\text{MapTRv2}^{\star}$ [ 19 ]	24	49.9	34.7	25.7	36.7
Mask2Map [ 8 ]	24	62.9	52.3	48.9	54.7
PredMapNet (Ours)	24	69.3	60.1	63.5	64.3

Table 3: Comparison of SOTA methods on nuScenes validation set (old split [ 19 ] ) with rasterization-based metric. The ”

\star

” indicates results reproduced using public codes.

Figure 3: Qualitative visualization on nuScenes val set.

Dataset	Method	$m$ AP $\uparrow$	C- $m$ AP $\uparrow$
nuScenes	StreamMapNet [ 39 ]	33.5	22.2
	MapTracker [ 5 ]	40.3	32.5
	PredMapNet (Ours)	42.1	33.7
Argoverse2	StreamMapNet [ 39 ]	64.4	54.4
	MapTracker [ 5 ]	70.3	61.3
	PredMapNet (Ours)	71.2	62.3

Table 4: Comparisons on non-overlapping datasets.

	$AP_{ped}$	$AP_{divider}$	$AP_{boundary}$	$m$ AP $\uparrow$
Baseline	77.3	72.4	74.2	74.7
+Semantic-Aware Query 3.2	77.2	73.1	74.7	75.0
+History-Map Guidance 3.4	77.6	73.6	75.0	75.4
+Short-Term Future Guidance 3.5	78.1	74.7	76.1	76.3
+Aux Depth Supervision	79.0	75.2	76.5	76.9

Table 5: Ablation study of main components of PredMapNet

HD Map Construction

High-definition map construction turns sensor and geographic data into precise, structured road maps for autonomous driving and simulation.

See all 39 papers

MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction
Aug 5, 2026Hyeonseo Kim, Juyeb Shin, Hyeonjun Jeong +2HD Map Construction Semantic Mapping
Robotics Program, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea · Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea
Driver2Map: Imitating Human Driving for Online High-Definition Map Construction
Aug 2, 2026Pan Yin, Runtian Xia, Weisong Kuang +3HD Map Construction Multimodal Sensor Fusion
Xi’an Jiaotong University
GSMap: 2D Gaussians for Online HD Mapping
May 10, 2026Zhenxuan Zeng, Lingxuan Wang, Sheng Yang +4HD Map Construction Geospatial Representation Learning
School of Computer Science, Northwestern Polytechnical University, China · Unmanned Vehicle Dept, Cainiao Inc., Alibaba Group, China

Aug 5, 2026J/K move · Enter open · S save

MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction

Hyeonseo Kim, Juyeb Shin, Hyeonjun Jeong, Hiwon Shin+1

Robotics Program, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea · Cho Chun Shik Graduate School of Mobility, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea

HD Map Construction Semantic Mapping Temporal Consistency

Open paper AskPDF arXiv

Constructing reliable online HD maps remains challenging in dynamic urban environments due to moving objects and occlusions. While recent works employ feature-level temporal fusion to address this, they rely solely on per-frame ground truth supervision. Consequently, they lack an explicit objective to directly penalize the geometric noise and temporal jitter between consecutive online HD maps. To address this, we propose MapTCL, an auxiliary training strategy that formulates temporal consistency loss between current and past frames via bidirectional alignment. Specifically, Bidirectional Vector Consistency Learning (BVCL) models the geometric and semantic discrepancies between associated past and current vector instances as an auxiliary loss. We also employ Raster map Consistency Learning (RCL) as an additional loss to stabilize dense BEV features. By jointly training with these dual losses, MapTCL improves the temporal stability of generated HD maps. Extensive experiments on two standard benchmarks demonstrate the effectiveness of our approach. As a versatile plug-and-play module, MapTCL consistently enhances existing baseline models, achieving gains of +3.7 mAP & +2.8 C-mAP on nuScenes and +3.1 mAP & +2.5 C-mAP on Argoverse 2 without additional inference overhead.

Abstract

HD Map Construction

Explore similar work

MapTCL: Temporal Consistency Learning via Bidirectional Alignment for Vectorized HD Map Construction

Driver2Map: Imitating Human Driving for Online High-Definition Map Construction

GSMap: 2D Gaussians for Online HD Mapping