AI Paper Atlas

Research map / 3D vision / Depth and stereo

SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration

Antoine Guedon, Pascal Monasse, Vincent Lepetit

NeurIPS 2022 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
use SCONE instead of PC-NBVSCONE · ShapeNet seen categoriesmean AUC: 0.716 -> 0.729Improved
use SCONE instead of PC-NBVSCONE · ShapeNet unseen categoriesmean AUC: 0.750 -> 0.764Improved
use SCONE instead of PC-NBVSCONE · ShapeNet CarAUC: 0.612 -> 0.591Hurt
use SCONE instead of PC-NBVSCONE · ShapeNet Pistol (unseen)AUC: 0.672 -> 0.717Improved
use SCONE instead of Random view selectionSCONE · ShapeNet seen categoriesmean AUC: 0.662 -> 0.729Improved
remove multi-scale neighborhood features from occupancy module (ablation)SCONE occupancy module · Occupancy prediction (MSE/IoU)MSE and IoUHurt
add camera history harmonics as extra feature to occupancy module (ablation)SCONE occupancy module · Occupancy prediction (MSE/IoU)MSE and IoUNo clear effect
remove geometric (volumetric) prediction, use surface points with occupancy 1 (ablation)SCONE coverage gain module · Coverage gainKL divergenceHurt
remove spherical mappings of camera history (ablation)SCONE coverage gain module · Coverage gainKL divergenceHurt
use SCONE instead of random walk and SCONE-Entropy for path planningSCONE · 13 large 3D scenessurface coverage AUCImproved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy