arXiv subjects

Carsten Markgraf

Publications and source records attributed to Carsten Markgraf.

7 recordsLinked to original sources

arXiv2026

AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion

High-resolution aerial imagery has recently emerged as a complementary modality for automated driving perception and has shown potential to improve birds-eye-view (BEV) scene understanding when fused with onboard sensors. Prior work demonstrated performance gains for online high-definition (HD) map construction through aerial-onboard fusion; however, conventional end-to-end fusion does not fully exploit the structural information contained in aerial representations. In this work, we introduce AerialFusionMapNet, a fusion-based mapping framework with a structured two-stage training strategy that explicitly enhances the contribution of aerial features within a unified pipeline. The proposed training scheme enables more effective integration of structural aerial priors. On the nuScenes geographic split, AerialFusionMapNet achieves up to 54.7 mAP, improving over prior aerial-onboard fusion baselines from 48.8 mAP by +5.9 absolute and +12.1% relative. The results suggest that structured training design, rather than increased architectural complexity, plays a more decisive role in unlocking the full potential of aerial imagery for online HD map construction. Code and trained models are available at https://github.com/DriverlessMobility/AerialFusionMapNet.

cs.CV↗

arXiv2026

Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction

Bird's-eye-view (BEV) representations derived from multi-camera input have become a central interface for online high-definition (HD) map construction. However, most approaches rely solely on ego-centric supervision, requiring large-scale scene structure to be inferred from incomplete observations, occlusions, and diminishing information density at long range, where perspective effects and spatial sparsity hinder consistent structural reasoning. We introduce Cross-View Supervision (CVS), a representation learning paradigm that transfers geometric and topological priors from an ego-aligned overhead perspective into camera-based BEV encoders. Rather than adding auxiliary semantic losses, CVS aligns representations in a shared BEV feature space and distills globally consistent structural knowledge from a perspective-privileged teacher into the ego-centric backbone. This supervision enhances structural coherence without modifying the inference architecture or requiring overhead input at test time. Experiments on nuScenes using ego-aligned aerial imagery from the AID4AD cross-view extension demonstrate consistent improvements over StreamMapNet while maintaining identical camera-only inference. CVS yields +3.9mAP in the standard $60\times30\,\mathrm{m}$ region and +9.9mAP in the extended $100\times50\,\mathrm{m}$ setting, corresponding to a 44% relative gain at long range. These results highlight perspective-privileged structural supervision as a promising training principle for improving BEV representation learning in HD map construction.

cs.CV↗

arXiv2026

Cross-Stage Coherence in Hierarchical Driving VQA: Explicit Baselines and Learned Gated Context Projectors

Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We present a comparative study of cross-stage context passing on DriveLM-nuScenes using two complementary mechanisms. The explicit variant evaluates three prompt-based conditioning strategies on a domain-adapted 4B VLM (Mini-InternVL2-4B-DA-DriveLM) without additional training, reducing NLI contradiction by up to 42.6% and establishing a strong zero-training baseline. The implicit variant introduces gated context projectors, which extract a hidden-state vector from one stage and inject a normalized, gated projection into the next stage's input embeddings. These projectors are jointly trained with stage-specific QLoRA adapters on a general-purpose 8B VLM (InternVL3-8B-Instruct) while updating only approximately 0.5% of parameters. The implicit variant achieves a statistically significant 34% reduction in planning-stage NLI contradiction (bootstrap 95% CIs, p < 0.05) and increases cross-stage entailment by 50%, evaluated with a multilingual NLI classifier to account for mixed-language outputs. Planning language quality also improves (CIDEr +30.3%), but lexical overlap and structural consistency degrade due to the absence of driving-domain pretraining. Since the two variants use different base models, we present them as complementary case studies: explicit context passing provides a strong training-free baseline for surface consistency, while implicit gated projection delivers significant planning-stage semantic gains, suggesting domain adaptation as a plausible next ingredient for full-spectrum improvement.

cs.CV↗

arXiv2026

GENPACK: KPI-Guided Multi-Criteria Genetic Algorithm for Industrial 3D Bin Packing

The three-dimensional bin packing problem (3D-BPP) is a longstanding challenge in operations research and logistics. While classical heuristics and constructive methods can generate packings efficiently, they often fail to satisfy industrial requirements such as stability, balance, and handling feasibility. Metaheuristics such as genetic algorithms (GAs) offer greater flexibility, but pure GA approaches frequently struggle with efficiency, parameter sensitivity, and scalability to industrial order sizes. These limitations are particularly evident at real-world pallet dimensions, where even state-of-the-art methods often fail to produce robust, deployable solutions. We propose a KPI-guided GA-based pipeline for industrial 3D-BPP that integrates key performance indicators (KPIs) directly into a scalarized fitness function. The method combines a layer-based chromosome representation, domain-specific operators, and constructive heuristics to balance efficiency and feasibility. On the BED-BPP benchmark of 1,500 real-world orders, our GENPACK pipeline consistently outperforms heuristic and learning-based baselines, achieving up to 35% higher space utilization and 15-20% stronger surface support, while exhibiting lower variance across orders. These gains come at a modest runtime cost but remain practical for batch-scale deployment, yielding stable, balanced, and space-efficient packings.

cs.NE↗

arXiv2025

Fast globally optimal Truncated Least Squares point cloud registration with fixed rotation axis

Recent results showed that point cloud registration with given correspondences can be made robust to outlier rates of up to 95\% using the truncated least squares (TLS) formulation. However, solving this combinatorial optimization problem to global optimality is challenging. Provably globally optimal approaches using semidefinite programming (SDP) relaxations take hundreds of seconds for 100 points. In this paper, we propose a novel linear time convex relaxation as well as a contractor method to speed up Branch and Bound (BnB). Our solver can register two 3D point clouds with 100 points to provable global optimality in less than half a second when the axis of rotation is provided. Although it currently cannot solve the full 6DoF problem, it is two orders of magnitude faster than the state-of-the-art SDP solver STRIDE when solving the rotation-only TLS problem. In addition to providing a formal proof for global optimality, we present empirical evidence of global optimality using adversarial instances with local minimas close to the global minimum.

cs.CV↗

arXiv2025

AID4AD: Aerial Image Data for Automated Driving Perception

This work investigates the integration of spatially aligned aerial imagery into perception tasks for automated vehicles (AVs). As a central contribution, we present AID4AD, a publicly available dataset that augments the nuScenes dataset with high-resolution aerial imagery precisely aligned to its local coordinate system. The alignment is performed using SLAM-based point cloud maps provided by nuScenes, establishing a direct link between aerial data and nuScenes local coordinate system. To ensure spatial fidelity, we propose an alignment workflow that corrects for localization and projection distortions. A manual quality control process further refines the dataset by identifying a set of high-quality alignments, which we publish as ground truth to support future research on automated registration. We demonstrate the practical value of AID4AD in two representative tasks: in online map construction, aerial imagery serves as a complementary input that improves the mapping process; in motion prediction, it functions as a structured environmental representation that replaces high-definition maps. Experiments show that aerial imagery leads to a 15-23% improvement in map construction accuracy and a 2% gain in trajectory prediction performance. These results highlight the potential of aerial imagery as a scalable and adaptable source of environmental context in automated vehicle systems, particularly in scenarios where high-definition maps are unavailable, outdated, or costly to maintain. AID4AD, along with evaluation code and pretrained models, is publicly released to foster further research in this direction: https://github.com/DriverlessMobility/AID4AD.

cs.CV↗

arXiv2024

Lane Detection using Graph Search and Geometric Constraints for Formula Student Driverless

Lane detection is a fundamental task in autonomous driving. While the problem is typically formulated as the detection of continuous boundaries, we study the problem of detecting lane boundaries that are sparsely marked by 2D points with many false positives. This problem arises in the Formula Student Driverless (FSD) competition and is challenging due to its inherent ambiguity. Previous methods are inefficient and unable to find long-horizon solutions. We propose a deterministic algorithm called CLC that uses backtracking graph search with a learned likelihood function to overcome these limitations. We impose geometric constraints on the lane candidates to guarantee a geometrically sound lane. Our exhaustive search leads to finding the global optimum in 45% of instances, and the algorithm is overall robust to up to 50% false positives. Our algorithm runs in less than 15 ms on a single CPU core, meeting the low latency requirements of autonomous racing. We extensively evaluate our method on real data and realistic racetrack layouts, and show that it outperforms the state-of-the-art by detecting long lanes over 100 m with few (0.6%) critical failures. This allows our autonomous racecar to drive close to its physical limits on a previously unknown racetrack without being limited by perception. We release our dataset with realistic Formula Student racetracks to enable further research.

cs.RO↗