Research map / Vision-language and multimodal / Cross-modal learning
Modality-Agnostic Topology Aware Localization
Farhad Ghazvinian Zanjani, Ilia Karmanov, Hanno Ackermann, Daniel Dijkman, Simone Merlin, Max Welling, Fatih Porikli
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 |
|---|---|---|---|
| perturb 10% of object texture/appearance in test scenes (ablation) | OT-Isomap · iGibson camera localization | localization error (cm): 61.9 -> 61.87 ± 0.09 | No clear effect |
| perturb 20% of objects in test scenes (ablation) | OT-Isomap · iGibson camera localization | localization error (cm): 61.9 -> 62.2 ± 0.09 | No clear effect |
| perturb 30% of objects in test scenes (ablation) | OT-Isomap · iGibson camera localization | localization error (cm): 61.9 -> 62.82 ± 0.17 | Hurt |
| perturb 50% of objects in test scenes (ablation) | OT-Isomap · iGibson camera localization | localization error (cm): 61.9 -> 63.77 ± 0.14 | Hurt |
| perturb 70% of objects in test scenes (ablation) | OT-Isomap · iGibson camera localization | localization error (cm): 61.9 -> 64.07 ± 0.26 | Hurt |
Closest papers by meaning
- Neural Topological SLAM for Visual Navigation (CVPR 2020 · similarity 0.85)
- Modality-Invariant Visual Odometry for Embodied Vision (CVPR 2023 · similarity 0.84)
- Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation (NeurIPS 2026 · similarity 0.82)
- Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models (NeurIPS 2026 · similarity 0.82)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.81)
- CVGL: Causal Learning and Geometric Topology (NeurIPS 2025 · similarity 0.81)
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.
