Research map / 3D vision / Depth and stereo
Distinguishing the Indistinguishable: Exploring Structural Ambiguities via Geodesic Context
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use geodesic consistency and viewpoint-path context to disambiguate correspondences | SfM reconstruction · Temple of Heaven | registration correctness | Helped |
| Use geodesic consistency and viewpoint-path context to disambiguate correspondences | SfM reconstruction · Building | registration correctness | Helped |
| Use geodesic consistency and viewpoint-path context to disambiguate correspondences | SfM reconstruction · Cup | registration correctness | Helped |
| Use geodesic consistency rather than only background-context cues | SfM disambiguation · visually indistinguishable scenes | ambiguity correction | Helped |
| Use geodesic-aware preprocessing instead of [29] | SfM disambiguation · Berliner Dom | over-segmentation | Helped |
| Use geodesic-aware preprocessing instead of [29] | SfM disambiguation · Radcliffe Camera | over-segmentation | Helped |
| Use geodesic-aware preprocessing instead of [29] | SfM disambiguation · Oats | ambiguity correction | Helped |
| Use geodesic-aware preprocessing instead of [13] | SfM disambiguation · Cup | ambiguity correction | Helped |
| Use geodesic-aware preprocessing instead of [13] | SfM disambiguation · Building | ambiguity correction | Helped |
| Use geodesic-aware preprocessing instead of [13] | SfM disambiguation · Temple of Heaven | ambiguity correction | Helped |
| Rely on missing-correspondence or background-conflict cues alone | SfM disambiguation · visually indistinguishable scenes | ambiguity correction | Hurt |
| Require sufficient viewpoint overlap between images | geodesic-aware method · scenes with widely separated viewpoints | geodesic inference accuracy | Helped |
Closest papers by meaning
- Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features (CVPR 2025 · similarity 0.84)
- Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces (ICML 2026 · similarity 0.84)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.84)
- Uncovering and Shaping the Latent Representation of 3D Scene Topology in Vision-Language Models (NeurIPS 2026 · similarity 0.84)
- Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding (NeurIPS 2025 · similarity 0.84)
- Leveraging Camera Triplets for Efficient and Accurate Structure-from-Motion (CVPR 2024 · similarity 0.84)
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.