Research map / Vision-language and multimodal / Robot action and navigation
monoVLN: Bridging the Observation Gap between Monocular and Panoramic Vision and Language Navigation
Renjie Lu, Yu Zhou, Hao Cheng, Jingke Meng, Wei-Shi Zheng
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 UAP active perception (ablation) | monoVLN baseline · R2R-CE val unseen | SR: 51.1 -> 52.8 | Improved |
| add IPC implicit partial completion (ablation) | monoVLN baseline · R2R-CE val unseen | SR: 51.1 -> 54.0 | Improved |
| add both IPC and UAP (ablation) | monoVLN baseline · R2R-CE val unseen | SR: 51.1 -> 54.8 | Improved |
| add CLIP alignment to reconstruction-only training (ablation) | IPC module · R2R-CE val unseen | SR: 40.8 -> 53.0 | Improved |
| pretrain-then-finetune instead of joint training (ablation) | IPC module · R2R-CE val unseen | SR: 53.0 -> 54.0 | Improved |
| add UAP without initial rotation (ablation) | monoVLN · R2R-CE val unseen | SR: 45.6 -> 48.7 | Improved |
| add UAP with initial rotation (ablation) | monoVLN · R2R-CE val unseen | SR: 54.0 -> 54.8 | Improved |
| use UAP instead of 360 rotation at every step (ablation) | monoVLN · R2R-CE val unseen | SR: 54.2 -> 54.8 | Improved |
| use predicted-node direction instead of random view (ablation) | UAP · R2R-CE val unseen | SR: 54.2 -> 54.8 | Improved |
| use monoVLN instead of 3DFF | monocular VLN · R2R-CE val unseen | SR: 44.9 -> 54.8 | Improved |
| use monoVLN instead of previous monocular SOTA | monocular VLN · RxR-CE val unseen | SR: 25.5 -> 31.8 | Improved |
| raise entropy threshold toward 1 (fewer replans) (ablation) | UAP · R2R-CE | SR | Mixed |
Closest papers by meaning
- MonoDream: Monocular Vision-Language Navigation with Panoramic Dreaming (AAAI 2026 · similarity 0.91)
- AgentVLN: Towards Agentic Vision-and-Language Navigation (ECCV 2026 · similarity 0.90)
- Uncertainty-Aware Gaussian Map for Vision-Language Navigation (ICLR 2026 · similarity 0.89)
- GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation (CVPR 2026 · similarity 0.88)
- Volumetric Environment Representation for Vision-Language Navigation (CVPR 2024 · similarity 0.87)
- ImagineNav: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination (ICLR 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.
