AI Paper Atlas

Research map / 3D vision / 3D generation

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

Zeyu Hu, Xuyang Bai, Jiaxiang Shang, Runze Zhang, Jiayu Dong, Xin Wang, Guangyuan Sun, Hongbo Fu, Chiew-Lan Tai

ICCV 2021 · 3D vision › 3D generation · approach: Semantic scene completion · 76 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 geodesic mesh branch to the Euclidean-only network (ablation)VMNet · ScanNet v2 valmIoU: 71.0 -> 73.3Improved
add intra-domain attentive aggregation (ablation)Euclidean baseline · ScanNet v2 valmIoU: 70.2 -> 72.1Improved
add inter-domain attentive fusion (ablation)Baseline + Intra · ScanNet v2 valmIoU: 72.1 -> 73.3Improved
use scalar attention instead of vector attention (ablation)VMNet · ScanNet v2 valmIoU: 72.3 -> 73.3Improved
use scalar attention instead of EdgeConv (ablation)VMNet · ScanNet v2 valmIoU: 72.6 -> 73.3Improved
use VC then QEM instead of VC only for mesh simplification (ablation)VMNet · ScanNet v2 valmIoU: 72.3 -> 73.3Improved
apply VC on first two mesh levels before QEM instead of QEM only (ablation)VMNet · ScanNet v2 valmIoU: 72.9 -> 73.3Improved
use primal instead of dual inter-domain attention (ablation)VMNet · ScanNet v2 valmIoU: 72.8 -> 73.3Improved
decode in the geodesic domain instead of projecting back to voxels (Variant 1) (ablation)VMNet · ScanNet v2 valmIoU: 72.4 -> 73.3Improved
add mesh branch to the encoder too (Variant 2) (ablation)VMNet · ScanNet v2 valmIoU: 73.3 -> 73.4No clear effect
add more mesh levels to the geodesic branch (ablation)VMNet · ScanNet v2 valmIoUImproved
add geodesic information to sparse voxel network (VMNet vs MinkowskiNet)VMNet · ScanNet v2 testmIoU: 73.6 -> 74.6Improved

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