AI Paper Atlas

Research map / 3D vision / 3D generation

Learning Long-Range Information with Dual-Scale Transformers for Indoor Scene Completion

Ziqi Wang, Fei Luo, Xiaoxiao Long, Wenxiao Zhang, Chunxia Xiao

ICCV 2023 · 3D vision › 3D generation · approach: Semantic scene completion · 7 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
replace the global structure extractor with a CNN (ablation)DST-Net stage 1 · Matterport3DChamfer Distance (x10^-1): 0.22 -> 0.32Hurt
replace the region geometry generator with a CNN (ablation)DST-Net stage 1 · Matterport3DChamfer Distance (x10^-1): 0.22 -> 0.26Hurt
add contrastive attention training (CAT) (ablation)DST-Net stage 1 · Matterport3DChamfer Distance (x10^-1): 0.24 -> 0.22Improved
train stage 2 on fused target (stage-1 output fused with target) instead of GT (ablation)DST-Net full model · Matterport3DChamfer Distance (x10^-1): 0.46 -> 0.23Improved
add stage 1 before stage 2 (versus stage 2 only) (ablation)DST-Net · Matterport3DChamfer Distance (x10^-1): 0.49 -> 0.23Improved
add stage 2 refinement on top of stage 1 (ablation)DST-Net · Matterport3DChamfer Distance (x10^-1): 0.22 -> 0.23 (CD); recall 0.77 -> 0.78No clear effect
add CIoT loss (ablation)DST-Net stage 1 · Matterport3DChamfer Distance (x10^-1): 0.25 -> 0.22Improved
add structure loss LS (ablation)DST-Net stage 1 · Matterport3DChamfer Distance (x10^-1): 0.26 -> 0.22Improved
add depth loss LD to the other losses (ablation)DST-Net stage 1 · Matterport3DChamfer Distance (x10^-1): 0.29 -> 0.22Improved
use DST-Net instead of SG-NN on Matterport3D precisionscene completion · Matterport3D (394 test rooms)Precision: 0.62 -> 0.61Hurt
reduce input frames to 20% at test time (ablation)DST-Net · Matterport3DChamfer Distance (x10^-1): 0.23 (40%) -> 0.47 (20%)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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