Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection

• URL: http://arxiv.org/abs/2609.07590v1
• Date: Mon, 07 Sep 2026 15:03:36 GMT
• Title: Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object Detection
• Abstract summary: We present our solution to the LUMPI track of the UCF UrbanTwin Sim2Real LiDAR Challenge at the 6th DriveX Workshop, ECCV 2026.<n>The detector must be trained only on synthetic data and is evaluated on 50 held-out real LiDAR frames.<n>A separate 50-frame synthetic submission is evaluated for point-cloud realism.
• Score: 54.03436243843709
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present our solution to the LUMPI track of the UCF UrbanTwin Sim2Real LiDAR Challenge at the 6th DriveX Workshop, ECCV 2026. The detector must be trained only on synthetic data and is evaluated on 50 held-out real LiDAR frames; a separate 50-frame synthetic submission is evaluated for point-cloud realism. Our method addresses the Sim2Real gap at three levels. First, we align synthetic scans to the 50k-point test density and build a 30k-record training pool using UT-LUMPI geometry, RangeLDM-based sampling diversification, rare-class copy-paste, and pedestrian-oriented augmentation. Second, complementary DSVT detectors and Car/Bus PointPillars specialists are trained under the same synthetic-only constraint. Third, predictions are integrated by class-aware routing, asymmetric agreement fusion, constrained residual-recall supplementation, class-coverage auditing, and selective box-size calibration. The realism branch is optimized independently with radial-density matching, weak affine calibration, and calibrated set mixing. The final submission obtains a Combined Score of 0.4692, a Detection Score of 0.1797, a Realism Score of 0.9035, and 3D mAP@0.5 of 0.1258.

Related papers

• Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object Detection [54.03436243843709]
  This report presents a multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection.<n>The method organizes digital-twin scans, diffusion-redrawn scans, density-stabilized scans, and pedestrian morphology-aligned samples into a unified training pool with complementary roles.
  arXiv  Detail & Related papers  (2026-09-07T15:16:15Z)
• Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Multi-View Multi-Target Tracking [14.031215272664538]
  Multi-camera 3D perception systems for warehouse scenes are trained largely on synthetic data.<n>The resulting synthetic-to-real gap corrupts ground-plane localization and cross-camera identity association.<n>We argue instead that it enters the pipeline at three separable points: the camera calibration, the object shape prior, and the assumption that the object census is known.
  arXiv  Detail & Related papers  (2026-08-25T06:48:50Z)
• Sparse-LiDAR Prompting of Monocular Geometry Foundations: An Empirical Study Toward Long-Range Driving Depth [10.469394868633234]
  We present SLIM, the first adaptation of MoGe-2 to accept truly sparse LiDAR input.<n>On Virtual KITTI and CARLA, SLIM reduces the absolute error of the MoGe-2 baseline by approximately 39-51% at 100-150 m.
  arXiv  Detail & Related papers  (2026-05-26T02:12:15Z)
• SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs [56.07550353240028]
  We introduce SimulCost, the first benchmark targeting cost-sensitive parameter tuning in physics simulations.<n>SimulCost compares LLM tuning cost-sensitive parameters against traditional scanning approach in both accuracy and computational cost.<n>Each simulator's cost is analytically defined and platform-independent.
  arXiv  Detail & Related papers  (2026-03-11T05:00:48Z)
• On the Limitations of Ray-Tracing for Learning-Based RF Tasks in Urban Environments [4.097291451674696]
  We study the realism of Sionna v ray-tracing for outdoor cellular links in central Rome.<n>We vary the main simulation parameters, including path depth, diffuse/specular/refraction flags, carrier frequency, as well as antenna's properties.
  arXiv  Detail & Related papers  (2025-07-25T19:58:44Z)
• JiSAM: Alleviate Labeling Burden and Corner Case Problems in Autonomous Driving via Minimal Real-World Data [49.2298619289506]
  We propose a plug-and-play method called JiSAM, shorthand for Jittering augmentation, domain-aware backbone and memory-based Sectorized AlignMent.<n>In extensive experiments conducted on the famous AD dataset NuScenes, we demonstrate that, with SOTA 3D object detector, JiSAM is able to utilize the simulation data and only labels on 2.5% available real data to achieve comparable performance to models trained on all real data.
  arXiv  Detail & Related papers  (2025-03-11T13:35:39Z)
• Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection [28.40887130075552]
  Pseudo-targets undermine the training of an accurate detector. It injects noise into the student's training, leading to severe overfitting problems. We propose a systematic solution, termed ConsistentTeacher, to reduce the inconsistency.
  arXiv  Detail & Related papers  (2022-09-04T10:21:02Z)
• Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval [51.42470171051007]
  This paper tackles the Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning. By combining two fundamental learning approaches in DML, e.g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR. We show that Modality-Aware Triplet Hard Mining (MATHM) enhances the baseline with three types of pairwise learning.
  arXiv  Detail & Related papers  (2021-12-15T08:36:44Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.