atlas

Research map / 3D vision / Depth and stereo

Self-Supervised Super-Plane for Neural 3D Reconstruction

CVPR 2023 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 12 citations (OpenAlex)

Read the paperCheck 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 changedWhereMeasuredEffect
Add the self-supervised super-plane constraint (ablation)VolSDF* · ScanNetF-score: 0.589 -> 0.683Helped
Use the super-plane constraint instead of ground-truth plane segmentation (ablation)VolSDF* · ScanNetF-score: 0.658 -> 0.646No clear effect
Add auto-filtering to the super-plane constraint (ablation)VolSDF* with super-plane constraint · ScanNetF-score: 0.646 -> 0.668Helped
Add non-plane edge masking to the super-plane constraint (ablation)VolSDF* with super-plane constraint · ScanNetF-score: 0.646 -> 0.655Helped
Add both auto-filtering and non-plane edge masking (ablation)VolSDF* with super-plane constraint · ScanNetF-score: 0.646 -> 0.683Helped
Use super-planes rather than individual planes for the plane constraint (ablation)VolSDF* · ScanNetF-score: 0.658 -> 0.683Helped
Apply the S3P super-plane approachVolSDF · 7-ScenesF-score: 0.246 -> 0.483Helped

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