HM-3D

HM3D is a dataset that contains a large collection of 3D scenes and corresponding floor plans, used to evaluate floor plan-guided embodied navigation across various navigation tasks.

Papers using HM-3D (22)

Rate-nav: Region-aware Termination Enhancement For Zero-shot Object Navigation With Vision-language Models2025 · 3 citesRvn-bench: A Benchmark For Reactive Visual Navigation2026Stairway To Success: An Online Floor-aware Zero-shot Object-goal Navigation Framework Via Llm-driven Coarse-to-fine Exploration2025History-augmented Vision-language Models For Frontier-based Zero-shot Object Navigation2025Think, Remember, Navigate: Zero-shot Object-goal Navigation With Vlm-powered Reasoning2025MUVLA: Learning To Explore Object Navigation Via Map Understanding2025WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation2025Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration2025SemNav: A Model-Based Planner for Zero-Shot Object Goal Navigation Using Vision-Foundation Models2025History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation2025Imaginative World Modeling with Scene Graphs for Embodied Agent Navigation2025Think, Remember, Navigate: Zero-Shot Object-Goal Navigation with VLM-Powered Reasoning2025FOM-Nav: Frontier-Object Maps for Object Goal Navigation2025RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation2025RVN-Bench: A Benchmark for Reactive Visual Navigation2026AERR-Nav: Adaptive Exploration-Recovery-Reminiscing Strategy for Zero-Shot Object Navigation2026FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation2026FloVerse: Floor Plan-Guided Multi-Modal Navigation2026SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation2025EmbodiedSplat: 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 Understanding2025