Research map / 3D vision / Depth and stereo
MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction
Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, Andreas Geiger
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 monocular depth and normal cues (ablation) | MLP and Multi-Res Grid SDF · Replica | reconstruction quality | Improved |
| use both depth and normal cues instead of one (ablation) | MonoSDF · Replica | reconstruction quality | Improved |
| add monocular cues (ablation) | Multi-Res Grids · Replica | convergence speed: 5k vs. 200k iterations (40x) | Improved |
| dense SDF grid instead of single MLP (ablation) | SDF representation without cues · Replica | reconstruction quality | Hurt |
| Multi-Res feature grids instead of single-res grid (ablation) | SDF representation without cues · Replica | reconstruction quality | Improved |
| MLP instead of Multi-Res Grids | MonoSDF · ScanNet | reconstruction quality | Improved |
| add monocular cues | VolSDF / Multi-Res Grids · DTU 3-view | Chamfer distance | Improved |
| Multi-Res Grids instead of MLP | MonoSDF · DTU all views | Chamfer distance | Improved |
| anneal monocular loss weights to 0 (ablation) | MonoSDF · DTU | qualitative reconstruction | Improved |
Closest papers by meaning
- Iso-Points: Optimizing Neural Implicit Surfaces With Hybrid Representations (CVPR 2021 · similarity 0.90)
- Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids (CVPR 2023 · similarity 0.90)
- Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (NeurIPS 2022 · similarity 0.90)
- MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction (CVPR 2025 · similarity 0.90)
- NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (AAAI 2024 · similarity 0.90)
- UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections (NeurIPS 2024 · 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.
