AI Paper Atlas

Research map / 3D vision / Face and shape

Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction

Bo Yang, Sen Wang, Andrew Markham, Niki Trigoni

IJCV 2019 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 152 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
train with FASet two-stage algorithm instead of joint end-to-end training (ablation)AttSets · ShapeNet-r2n2 Group 4 (1 view)mean IoU: 0.307 -> 0.642Improved
train with FASet instead of joint training (ablation)AttSets · ShapeNet-r2n2 Group 4 (24 views)mean IoU: 0.680 -> 0.695Improved
use feature-wise instead of element-wise attention scores (ablation)AttSets · ShapeNet-r2n2 Group 4 (1 and 24 views)mean IoU: 24 views: 0.672 -> 0.695Improved
use element-wise attention instead of feature-wise (ablation)AttSets · ShapeNet-r2n2 Group 4 (2 views)mean IoU: 0.660 -> 0.653Hurt
use fc attention instead of conv2d attention (ablation)AttSets · ShapeNet-r2n2 Group 4 (24 views)mean IoU: 0.676 -> 0.695Improved
use fc instead of conv3d attention (ablation)AttSets · ShapeNet-r2n2 Group 4 (24 views)mean IoU: 0.690 -> 0.695No clear effect
replace GRU with AttSetsBase_r2n2 · ShapeNet-r2n2 Group 5 (24 views)mean IoU: 0.651 -> 0.694Improved
replace mean pooling with AttSetsBase_r2n2 · ShapeNet-r2n2 Group 5 (1 view)mean IoU: 0.598 -> 0.642Improved
replace max pooling with AttSetsBase_r2n2 · ShapeNet-lsm (1 view)mean IoU: 0.276 -> 0.404Improved
replace max pooling with AttSetsBase_r2n2 · ModelNet40 Group 2 (1 view)mean IoU: 0.461 -> 0.487Improved
replace max pooling with AttSetsBase_silnet · Blobby Group 2 (4 views)mean IoU: 0.929 -> 0.937Improved
fine-tune pooling baselines with random N in [1,24] instead of fixed N=24 (ablation)max pooling · ShapeNet-r2n2 (1 view)mean IoU: 0.504 -> 0.601Improved

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