Alternatives and similar repositories for OVSG

Users that are interested in OVSG are comparing it to the libraries listed below

• BIT-DYN / OpenGraph
  [RAL 2024] OpenGraphs: Open-Vocabulary Hierarchical 3D Scene Graphs in Large-Scale Outdoor Environments
  ☆105Updated 2 months ago
• XiaohanLei / IEVE
  PyTorch implementation of CVPR 2024 paper: Instance-aware Exploration-Verification-Exploitation for Instance ImageGoal Navigation
  ☆27Updated 6 months ago
• MrZihan / Sim2Real-VLN-3DFF
  Official implementation of Sim-to-Real Transfer via 3D Feature Fields for Vision-and-Language Navigation (CoRL'24).
  ☆65Updated 3 months ago
• honghd16 / GSA-VLN
  Official repository of General Scene Adaptation for Vision-and-Language Navigation (ICLR'2025)
  ☆40Updated last month
• MrZihan / NavRAG
  Official implementation of "NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM" (ACL'25 …
  ☆35Updated 3 months ago
• bagh2178 / UniGoal
  [CVPR 2025] UniGoal: Towards Universal Zero-shot Goal-oriented Navigation
  ☆136Updated 2 weeks ago
• Xiaohao-Xu / SLAM-under-Perturbation
  [ICLR 2025] Scalable Benchmarking and Robust Learning for Noise-Free Ego-Motion and 3D Reconstruction from Noisy Video
  ☆55Updated last month
• ai4ce / CityWalker
  [CVPR 2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
  ☆93Updated 2 months ago
• behretj / LostFound
  [RA-L] Lost & Found dynamically tracks object poses from egocentric videos while updating a scene graph, enabling richer semantic 3D unde…
  ☆43Updated last month
• BJHYZJ / DovSG
  [RA-L 2025] Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation
  ☆78Updated last month
• boschresearch / Open3DSG
  [CVPR 2024] Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
  ☆110Updated 8 months ago
• OpenRobotLab / VLM-Grounder
  [CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
  ☆107Updated 2 weeks ago
• sx-zhang / SGM
  Imagine Before Go: Self-Supervised Generative Map for Object Goal Navigation (CVPR2024)
  ☆42Updated 2 months ago
• Gary3410 / eif_unknown
  Embodied Instruction Following in Unknown Environments
  ☆11Updated 2 months ago
• wzcai99 / NavDP
  Official implementation of the paper: "NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance"
  ☆51Updated last week
• MrZihan / GridMM
  Official implementation of GridMM: Grid Memory Map for Vision-and-Language Navigation (ICCV'23).
  ☆90Updated last year
• XiaohanLei / GaussNav
  PyTorch implementation of paper: GaussNav: Gaussian Splatting for Visual Navigation
  ☆125Updated 6 months ago
• BIT-DYN / OpenObj
  [RAL 2024] OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding
  ☆27Updated 3 months ago
• ai4ce / MSG
  [NeurIPS2024] Multiview Scene Graph (topologically representing a scene from unposed images by interconnected place and object nodes)
  ☆112Updated 4 months ago
• jzhzhang / 3DAwareNav
  [CVPR 2023] We propose a framework for the challenging 3D-aware ObjectNav based on two straightforward sub-policies. The two sub-polices,…
  ☆72Updated last year
• Ram81 / goat-bench
  ☆98Updated 10 months ago
• MIT-SPARK / llm_scene_understanding
  ☆84Updated last year
• peiqi-liu / stretch_ai
  ☆14Updated 2 weeks ago
• shiyoung77 / OVIR-3D
  This is the official repository for OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data. (CoRL'23)
  ☆106Updated last year
• Chenkehan21 / CA-Nav-code
  ☆28Updated last week
• XinyuSun / PSL-InstanceNav
  official implementation for ECCV 2024 paper "Prioritized Semantic Learning for Zero-shot Instance Navigation"
  ☆36Updated 8 months ago
• roomtour3d / roomtour3d-NaviLLM
  [CVPR 2025] RoomTour3D - Geometry-aware, cheap and automatic data from web videos for embodied navigation
  ☆49Updated 2 months ago
• HaochenZ11 / VLA-3D
  ☆62Updated 4 months ago
• MIT-SPARK / Clio
  ☆178Updated 3 months ago
• MrZihan / g3D-LF
  Official implementation of "g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks" (CVPR'25).
  ☆21Updated last month