HM-3D

HM-3D is a dataset that contains a collection of 3D scenes used to evaluate floor plan-guided embodied navigation tasks, including PointNav, ObjectNav, and ImageNav.

Papers using HM-3D (23)

Rate-nav: Region-aware Termination Enhancement For Zero-shot Object Navigation With Vision-language Models2025 · 3 citesHRO: Hierarchical Room-to-Object Framework for Zero-Shot Object Goal Navigation with Large Language Models2026FloVerse: Floor Plan-Guided Multi-Modal Navigation2026SurveilNav: Collaborative Object Goal Navigation with Robot and Surveillance System2026PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making2026TravExplorer: Cross-Floor Embodied Exploration via Traversability-Aware 3-D Planning2026Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration2026FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation2026RVN-Bench: A Benchmark for Reactive Visual Navigation2026AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation2026FOM-Nav: Frontier-Object Maps for Object Goal Navigation2025RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation2025Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning2025EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device2025PersONAL: Towards a Comprehensive Benchmark for Personalized Embodied Agents2025MUVLA: Learning to Explore Object Navigation via Map Understanding2025Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation2025SemNav: A Model-Based Planner for Zero-Shot Object Goal Navigation Using Vision-Foundation Models2025History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation2025SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation2025Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation2025Ground-level Viewpoint Vision-and-Language Navigation in Continuous Environments2025