cs.CVNov 3, 2026

BhopalMLS: A LiDAR Dataset for Semantic Scene Understanding in Heterogeneous Urban Environments

Authors: Pyare Lal Chauhan, Vaibhav Kumar, Bharat Lohani

Organizations: GeoAI4Cities Lab, Department of Data Science and Engineering, IISER Bhopal, India · Department of Civil Engineering, IIT Kanpur, India

Abstract

We introduce BhopalMLS, a large-scale Mobile Laser Scanning (MLS) dataset from a dense, heterogeneous urban environment in Bhopal, India, with mixed traffic, informal structures, and narrow unplanned streets. It spans approximately 10 km of road corridors with over 1.2 billion points and 19,518 annotated instances across 62 fine-grained static categories, grouped into 12-class and 21-class benchmark taxonomies; 6 optional moving-class subclasses support dynamic-object analysis. Existing 3D datasets, collected in well-planned cities, are structurally more uniform than such unplanned settings, and lack their subtype diversity. On semantic and instance segmentation at both granularities, fine-tuned foundation models surpass supervised baselines: Utonia(L) reaches 71.28% mIoU (vs. PTv3's 68.04% from scratch) and 44.07% mAP50 on the 12-class benchmark. Cross-region experiments against four established datasets (Ke-MLS, Toronto-3D, Paris-Lille-3D, SemanticKITTI) reveal a consistent asymmetric transferability: models trained on BhopalMLS transfer better than the reverse on every pair, for both Utonia(L) and Concerto(L) (mean 21.5, up to 36 mIoU points), holding even when the target is denser. Factor-controlled retraining at a fixed label budget, repeated on both models, attributes this to the coverage of BhopalMLS's subtype inventory rather than to dataset size or corridor geometry: collapsing each class to a single subtype costs 13.0 and 13.3 mIoU points for Utonia(L) and Concerto(L). BhopalMLS therefore offers a testbed for 3D perception beyond well-planned cities. Data and an interactive viewer are at https://geoai4cities.github.io/bhopalmls.

Figures & tables

Appendix figures & tables26 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Semantic-ITC: A Frame-wise Indoor Mobile Laser Scanning Dataset and Benchmark for Semantic Segmentation

    Sep 16, 2026Haiyang Wu, Muhammad Affan, George Vosselman +13D Semantic Segmentation3D Point Cloud Segmentation

  2. Multi-modal panoramic 3D outdoor datasets for place categorization

    Apr 14, 2026Hojung Jung, Yuki Oto, Oscar M. Mozos +23D Scene UnderstandingMultimodal Classification

  3. 3DCity-LLM: Empowering Multi-modality Large Language Models for 3D City-scale Perception and Understanding

    Mar 24, 2026Yiping Chen, Jinpeng Li, Wenyu Ke +63D VLMs3D Scene Understanding