Research map / 3D vision / 3D generation
Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning
Sixian Zhang, Yiyao Wang, Xinhang Song, Keming Zhang, Zijian Xu, Shuqiang Jiang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add instance unit and indexing grid (ablation) | VLFM · ObjectNav (HM3D) | SR (%): 52.5 -> 57.4 | Improved |
| add instance unit and indexing grid (ablation) | VLFM · ObjectNav (HM3D) | SPL (%): 30.4 -> 31.3 | Improved |
| add region unit and indexing grid (ablation) | VLFM · ObjectNav (HM3D) | SR (%): 52.5 -> 56.2 | Improved |
| add region unit and indexing grid (ablation) | VLFM · ObjectNav (HM3D) | SPL (%): 30.4 -> 30.9 | Improved |
| add region unit on top of instance unit (ablation) | GLMap · ObjectNav (HM3D) | SR (%): 57.4 -> 59.1 | Improved |
| add instance unit on top of region unit (ablation) | GLMap · ObjectNav (HM3D) | SR (%): 56.2 -> 59.1 | Improved |
| add region unit on top of instance unit (ablation) | GLMap · ObjectNav (HM3D) | SPL (%): 31.3 -> 32.2 | Improved |
| add GLMap to LLM-based method | ESC · ObjectNav (HM3D) | SR (%): 39.2 -> 48.8 | Improved |
| add GLMap to LLM-based method | ESC · ObjectNav (HM3D) | SPL (%): 22.3 -> 25.2 | Improved |
| add GLMap to VLM-based method | ApexNAV · ObjectNav (HM3D) | SR (%): 59.6 -> 62.7 | Improved |
| add GLMap to VLM-based method | ApexNAV · ObjectNav (HM3D) | SPL (%): 33.0 -> 33.7 | Improved |
| add GLMap to MLLM-based method | GPT4Scene · SQA3D | EM-1 (%): 57.2 -> 58.5 | Improved |
Closest papers by meaning
- GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance (NeurIPS 2024 · similarity 0.89)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.89)
- g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks (CVPR 2025 · similarity 0.87)
- GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding (CVPR 2025 · similarity 0.87)
- LangMap: A Human-Verified Benchmark for Hierarchical Open-Vocabulary Goal Navigation (NeurIPS 2026 · similarity 0.87)
- OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
