AI Paper Atlas

Research map / 3D vision / 3D generation

SSR-2D: Semantic 3D Scene Reconstruction From 2D Images

Junwen Huang, Alexey Artemov, Yujin Chen, Shuaifeng Zhi, Kai Xu, Matthias Nießner

TPAMI 2024 · 3D vision › 3D generation · approach: Semantic scene completion · 9 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
add virtual view selection (2D GT labels) (ablation)Ours · Matterport3D SGmIoU (%): 26.9 -> 30.1Improved
add virtual view selection (pseudo-labels) (ablation)Ours · Matterport3D SGmIoU (%): 20.5 -> 21.5Improved
increase virtual views from 5 to 15 (2D GT) (ablation)Ours · Matterport3D SGmIoU (%): 30.1 -> 32.6Improved
add geometry completion head (ablation)Ours · Matterport3D SGmIoU (%): 32.8 -> 36.7Improved
add color encoder (ablation)Ours · Matterport3D SSCmIoU (%): 22.4 -> 28.6Improved
add color decoder (ablation)Ours · Matterport3D SSCmIoU (%): 26.3 -> 28.6Improved
train with both 2D and 3D ground truth instead of 2D only (ablation)Ours · Matterport3D SSCmIoU (%): 30.1 -> 35.1Improved
use machine-generated 2D pseudo-labels instead of 2D GT (ablation)Ours · Matterport3D SSCmIoU (%): 30.1 -> 21.5Hurt
increase input frame completeness from 30-40% to 40-50% (ablation)Ours · Matterport3D SGmIoU (%): 36.7 -> 40.4Improved
train on ScanNet and test on Matterport3D instead of in-domain (ablation)Ours · Matterport3D SSC (cross-data)mIoU (%): 36.7 -> 17.9Hurt
use Ours instead of Semantic-NeRFOurs · ScanNet SSCGeo. mIoU: 3.9 -> 49.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most 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

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