atlas

Research map / 3D vision / 3D generation

Panoptic 3D Scene Reconstruction From a Single RGB Image

NeurIPS 2021 · 3D vision › 3D generation · approach: Semantic scene completion · 8 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
Jointly reconstruct geometry, semantics, and instances with 2D-to-3D feature and instance propagationPanoptic 3D scene reconstruction · 3D-Front testPRQ: 15.08 -> 42.60Helped
Jointly reconstruct geometry, semantics, and instances with 2D-to-3D feature and instance propagationPanoptic 3D scene reconstruction · Matterport3D testPRQ: 6.29 -> 6.34Helped
Add 2D-to-3D instance propagation instead of 3D instance clustering (ablation)Ours · 3D-Front testPRQ: 19.76 -> 42.60Helped
Add progressive coarse-to-fine hierarchy predictions (ablation)Ours · 3D-Front testPRQ: 41.53 -> 42.60Helped
Add additional lifted 2D image features (ablation)Ours · 3D-Front testPRQ: 41.53 -> 42.60Helped
Add 3D refinement and completion (ablation)Ours · 3D-Front test, thingsPRQ: 5.21 -> 36.79Helped
Use ground-truth rather than predicted depth (ablation)Ours · 3D-Front testPRQ: 42.60 -> 44.58Helped

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