AI Paper Atlas

Research map / 3D vision / 3D generation

Global-Aware Monocular Semantic Scene Completion with State Space Models

Shijie Li, Zhongyao Cheng, Rong Li, Shuai Li, Juergen Gall, Xun Xu, Xulei Yang

ICCV 2025 · 3D vision › 3D generation · approach: Semantic scene completion · 1 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 3D conv blocks with Mamba blocks in the decoder (ablation)GA-MonoSSC · Occ-ScanNet-minimIoU: 46.83 -> 48.19Improved
replace 3D conv blocks with Mamba blocks in the decoder (ablation)GA-MonoSSC · NYUv2mIoU: 31.6 -> 32.32Improved
add frustum reordering of voxels before Mamba (ablation)GA-MonoSSC · Occ-ScanNet-minimIoU: 46.66 -> 48.19Improved
add frustum reordering of voxels before Mamba (ablation)GA-MonoSSC · NYUv2IoU: 47.1 -> 47.51Improved
add multi-scale feature learning (ablation)GA-MonoSSC · Occ-ScanNet-minimIoU: 47.39 -> 48.19Improved
learn semantic and geometric features separately (multi-modality) (ablation)GA-MonoSSC · Occ-ScanNet-minimIoU: 46.2 -> 48.19Improved
learn multi-modality and multi-scale features together (ablation)GA-MonoSSC · Occ-ScanNet-minimIoU: 46.07 -> 48.19Improved
supervise geometry decoder with 3D occupancy instead of 2D depth (ablation)GA-MonoSSC · NYUv2mIoU: 31.65 -> 32.32Improved
inject geometry features into semantic decoder (geo->sem) vs none (ablation)GA-MonoSSC · NYUv2mIoU: 32.0 -> 32.32Improved
inject semantic features into geometry decoder (sem->geo) (ablation)GA-MonoSSC · NYUv2mIoU: 32.0 -> 31.61Hurt
make geometry and semantic decoders interact in both directions (ablation)GA-MonoSSC · NYUv2mIoU: 32.32 -> 32.07No clear effect
use GA-MonoSSC instead of ISOGA-MonoSSC · Occ-ScanNetmIoU: 28.71 -> 35.65Improved

Earlier methods this paper compares with

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