Chuanrui Hu, Xingze Gao, Zuyi Zhou, Dannong Xu, Yi Bai, Xintong Li, Hui Zhang, Tong Li, Chong Zhang, Lidong Bing, Yafeng Deng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Vectorized High-Definition (HD) map construction requires predictions of the category and point coordinates of map elements (e.g. road boundary, lane divider, pedestrian crossing, etc.). State-of-the-art methods are mainly based on point-level representation learning for regressing accurate point coordinates. However, this pipeline has limitations in obtaining element-level information and handling element-level failures, e.g. erroneous element shape or entanglement between elements. To tackle the above issues, we propose a simple yet effective HybrId framework named HIMap to sufficiently learn and interact both point-level and element-level information. Concretely, we introduce a hybrid representation called HIQuery to represent all map elements, and propose a point-element interactor to interactively extract and encode the hybrid information of elements, e.g. point position and element shape, into the HIQuery. Additionally, we present a point-element con-sistency constraint to enhance the consistency between the point-level and element-level information. Finally, the output point-element integrated HIQuery can be directly converted into map elements' class, point coordinates, and mask. We conduct extensive experiments and consistently outperform previous methods on both nuScenes and Argo-verse2 datasets. Notably, our method achieves 77.8 mAP on the nuScenes dataset, remarkably superior to previous SOTAs by 8.3 mAP at least.

HD map construction is a fundamental and challenging task in autonomous driving to understand the surrounding environment. Recently, Camera-LiDAR BEV feature fusion methods have attracted increasing attention in HD map construction task, which can significantly boost the benchmark. However, existing fusion methods ignore modal interaction and utilize very simple fusion strategy, which suffers from the problems of misalignment and information loss. To tackle this, we propose a novel Multi-modal BEV feature fusion method named MBFusion. Specifically, to solve the semantic misalignment problem between Camera and LiDAR features, we design Cross-modal Interaction Transform (CIT) module to make these two feature spaces interact knowledge with each other to enhance the feature representation by the cross-attention mechanism. Then, we propose a Dual Dynamic Fusion (DDF) module to automatically select valuable information from different modalities for better feature fusion. Moreover, MBFusion is simple, and can be plug-and-played into existing pipelines. We evaluate MBFusion on three architectures, including HDMapNet, VectorMapNet, and MapTR, to show its versatility and effectiveness. Compared with the state-of-the-art methods, MBFusion achieves 3.6% and 4.1% absolute improvements on mAP on the nuScenes and the Argoverse2 datasets, respectively, demonstrating the superiority of our method.

Driving systems often rely on high-definition (HD) maps for precise environmental information, which is crucial for planning and navigation. While current HD map constructors perform well under ideal conditions, their resilience to real-world challenges, \eg, adverse weather and sensor failures, is not well understood, raising safety concerns. This work introduces MapBench, the first comprehensive benchmark designed to evaluate the robustness of HD map construction methods against various sensor corruptions. Our benchmark encompasses a total of 29 types of corruptions that occur from cameras and LiDAR sensors. Extensive evaluations across 31 HD map constructors reveal significant performance degradation of existing methods under adverse weather conditions and sensor failures, underscoring critical safety concerns. We identify effective strategies for enhancing robustness, including innovative approaches that leverage multi-modal fusion, advanced data augmentation, and architectural techniques. These insights provide a pathway for developing more reliable HD map construction methods, which are essential for the advancement of autonomous driving technology. The benchmark toolkit and affiliated code and model checkpoints have been made publicly accessible.

Depth-aware Video Panoptic Segmentation (DVPS) is a challenging task that requires predicting the semantic class and 3D depth of each pixel in a video, while also segmenting and consistently tracking objects across frames. Predominant methodologies treat this as a multi-task learning problem, tackling each constituent task independently, thus restricting their capacity to leverage interrelationships amongst tasks and requiring parameter tuning for each task. To surmount these constraints, we present Slot-IVPS, a new approach employing an object-centric model to acquire unified object representations, thereby facilitating the model's ability to simultaneously capture semantic and depth information. Specifically, we introduce a novel representation, Integrated Panoptic Slots (IPS), to capture both semantic and depth information for all panoptic objects within a video, encompassing background semantics and foreground instances. Subsequently, we propose an integrated feature generator and enhancer to extract depth-aware features, alongside the Integrated Video Panoptic Retriever (IVPR), which iteratively retrieves spatial-temporal coherent object features and encodes them into IPS. The resulting IPS can be effortlessly decoded into an array of video outputs, including depth maps, classifications, masks, and object instance IDs. We undertake comprehensive analyses across four datasets, attaining state-of-the-art performance in both Depth-aware Video Panoptic Segmentation and Video Panoptic Segmentation tasks.

Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel, uniquely segmenting and identifying all object instances consistently across all frames. Classic solutions usually decompose the VPS task into several subtasks and utilize multiple surrogates (e.g. boxes and masks, centers and offsets) to represent objects. However, this divide-and-conquer strategy requires complex post-processing in both spatial and temporal domains and is vulnerable to failures from surrogate tasks. In this paper, inspired by object-centric learning which learns compact and robust object representations, we present Slot- VPS, the first end-to-end framework for this task. We encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation called panoptic slots. The coherent spatio-temporal object's information is retrieved and encoded into the panoptic slots by the proposed Video Panoptic Retriever, enabling to localize, segment, differentiate, and associate objects in a unified manner. Finally, the output panoptic slots can be directly converted into the class, mask, and object ID of panoptic objects in the video. We conduct extensive ablation studies and demonstrate the effectiveness of our approach on two benchmark datasets, Cityscapes- VP S (val and test sets) and VIPER (val set), achieving new state-of-the-art performance of 63.7, 63.3 and 56.2 VPQ, respectively.