Research map / Vision-language and multimodal / Robot action and navigation
Uncertainty-Aware Gaussian Map for Vision-Language Navigation
Jianzhe Gao, Rui Liu, Yuxuan Xu, Tongtong Cao, Yingxue Zhang, Zhanguang Zhang, Sida Peng, Yi Yang, Wenguan Wang
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 Semantic Gaussian Map (SGM) as 3D scene representation (ablation) | DUET-based agent · REVERIE val unseen | RGS: 32.15 -> 35.48 | Improved |
| add uncertainty values only (no raw Gaussians) (ablation) | DUET-based agent · R2R val unseen | SR: 72.22 -> 74.20 | Improved |
| add 3D Value Map uncertainty on top of SGM (ablation) | SGM agent · R2R val unseen | SR: 76.21 -> 78.32 | Improved |
| add geometric and semantic uncertainty to SGM (ablation) | SGM agent · REVERIE val unseen | RGS: 35.48 -> 36.96 | Improved |
| add appearance uncertainty alone to SGM (ablation) | SGM agent · REVERIE val unseen | RGS: 35.48 -> 35.68 | Improved |
| add all three uncertainties vs appearance alone (ablation) | SGM agent · REVERIE val unseen | RGS: 35.68 -> 37.65 | Improved |
| slightly prune low-scale and low-opacity Gaussians (tau_e 0.01, tau_alpha 0.002) (ablation) | SGM agent · R2R val unseen | SR: 77.30 -> 77.87 | Improved |
| moderate pruning (tau_e 0.015, tau_alpha 0.005) (ablation) | SGM agent · R2R val unseen SR and FPS | SR / FPS: SR 77.30 -> 78.32; FPS 11.2 -> 15.5 | Improved |
| aggressive pruning (tau_e 0.02, tau_alpha 0.010) (ablation) | SGM agent · R2R val unseen | SR: 78.32 -> 74.80 | Hurt |
| use full agent instead of VER on R2R test unseen | Ours · R2R test unseen | SR: 76 vs 76 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DUET — DUET: Cross-Modal Semantic Grounding for Contrastive Zero-Shot Learning (AAAI 2023) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation (ICCV 2025 · similarity 0.92)
- GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation (CVPR 2026 · similarity 0.88)
- FUSE: Quantifying Uncertainty in Vision-Language Models by Bayesian Fusing Epistemic and Aleatoric Uncertainty (ICML 2026 · similarity 0.88)
- BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation (NeurIPS 2025 · similarity 0.88)
- Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation (NeurIPS 2025 · similarity 0.88)
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation (NeurIPS 2025 · similarity 0.88)
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.
