Research map / 3D vision / Depth and stereo
SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration
Antoine Guedon, Pascal Monasse, Vincent Lepetit
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 |
|---|---|---|---|
| use SCONE instead of PC-NBV | SCONE · ShapeNet seen categories | mean AUC: 0.716 -> 0.729 | Improved |
| use SCONE instead of PC-NBV | SCONE · ShapeNet unseen categories | mean AUC: 0.750 -> 0.764 | Improved |
| use SCONE instead of PC-NBV | SCONE · ShapeNet Car | AUC: 0.612 -> 0.591 | Hurt |
| use SCONE instead of PC-NBV | SCONE · ShapeNet Pistol (unseen) | AUC: 0.672 -> 0.717 | Improved |
| use SCONE instead of Random view selection | SCONE · ShapeNet seen categories | mean AUC: 0.662 -> 0.729 | Improved |
| remove multi-scale neighborhood features from occupancy module (ablation) | SCONE occupancy module · Occupancy prediction (MSE/IoU) | MSE and IoU | Hurt |
| add camera history harmonics as extra feature to occupancy module (ablation) | SCONE occupancy module · Occupancy prediction (MSE/IoU) | MSE and IoU | No clear effect |
| remove geometric (volumetric) prediction, use surface points with occupancy 1 (ablation) | SCONE coverage gain module · Coverage gain | KL divergence | Hurt |
| remove spherical mappings of camera history (ablation) | SCONE coverage gain module · Coverage gain | KL divergence | Hurt |
| use SCONE instead of random walk and SCONE-Entropy for path planning | SCONE · 13 large 3D scenes | surface coverage AUC | Improved |
Later papers that compared with this method
1 later accepted paper reports SCONE as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision (CVPR 2023 · better on 2 of 2 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
- MACARONS: Mapping and Coverage Anticipation With RGB Online Self-Supervision (CVPR 2023 · similarity 0.87)
- GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction (CVPR 2024 · similarity 0.84)
- SC-NeuS: Consistent Neural Surface Reconstruction from Sparse and Noisy Views (AAAI 2024 · similarity 0.84)
- ViiNeuS: Volumetric Initialization for Implicit Neural Surface Reconstruction of Urban Scenes with Limited Image Overlap (CVPR 2025 · similarity 0.84)
- Semantic Complete Scene Forecasting from a 4D Dynamic Point Cloud Sequence (AAAI 2024 · similarity 0.83)
- LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels (CVPR 2024 · similarity 0.83)
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.
