AI Paper Atlas

Research map / 3D vision / 3D generation

Efficient Semantic Scene Completion Network with Spatial Group Convolution

Jiahui Zhang, Hao Zhao, Anbang Yao, Yurong Chen, Li Zhang, Hongen Liao

ECCV 2018 · 3D vision › 3D generation · approach: Semantic scene completion · 118 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 the proposed sparse conv network with multiscale encoder-decoder instead of SSCNetSGC sparse conv network · SUNCGsemantic scene completion avg IoU: 46.4 -> 70.5Improved
add SGC with 4 groups (fixed pattern partition) to baselineSGC sparse conv network · SUNCGsemantic scene completion avg IoU: 70.5 -> 69.3 with FLOPs 79G -> 22GHurt
add SGC with 2 random groupsSGC sparse conv network · SUNCGsemantic scene completion avg IoU: 70.5 -> 69.9 with FLOPs 79G -> 42GHurt
add SGC with 6 groups (pattern)SGC sparse conv network · SUNCGsemantic scene completion avg IoU: 70.5 -> 66.9 with FLOPs 79G -> 16GHurt
use fixed pattern partition instead of random partition with 4 groups (ablation)SGC sparse conv network · SUNCGsemantic scene completion avg IoU: 67.6 -> 69.3Improved
use fixed pattern partition instead of random partition with 3 groups (ablation)SGC sparse conv network · SUNCGscene completion IoU: 82.6 -> 84.1Improved
use fixed pattern partition instead of random with 2 groups (ablation)SGC sparse conv network · SUNCGsemantic scene completion avg IoU: 69.9 -> 69.6Mixed
add SGC with 4 groups (pattern) effect on small categories like chairSGC sparse conv network · SUNCGper-class IoU drop: -3.7 chair, -2.1 objs vs 0.2 ceilHurt
use fixed pattern partition instead of random, G=2 (ablation)SGC sparse conv network · NYUsemantic scene completion IoU: 24.1 -> 26.5Improved
use fixed pattern partition instead of random, G=4 (ablation)SGC sparse conv network · NYUsemantic scene completion IoU: 22.6 -> 25.9Improved
add SGC G=3 pattern partition to baselineSGC sparse conv network · NYUsemantic scene completion IoU: 26.4 -> 26.7No clear effect
add random-partition SGC G=3 to baselineSGC sparse conv network · NYUsemantic scene completion IoU: 26.4 -> 23Hurt

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