AI Paper Atlas

Research map / 3D vision / Face and shape

Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

Haozhe Xie, Hongxun Yao, Shengping Zhang, Shangchen Zhou, Wenxiu Sun

IJCV 2020 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 213 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 the refiner (ablation)Pix2Vox++/A · ShapeNet single-view (32^3)mean IoU: 0.658 -> 0.670Improved
use multi-scale context-aware fusion instead of average pooling fusion (ablation)Pix2Vox++/A · ShapeNet-Cars multi-view (128^3), 8 viewsmean IoU: 0.829 -> 0.843Improved
use multi-scale context-aware fusion instead of context-aware fusion (ablation)Pix2Vox++/A · ShapeNet-Cars multi-view (128^3), 8 viewsmean IoU: 0.801 -> 0.843Improved
use multi-scale context-aware fusion instead of average pooling fusion (ablation)Pix2Vox++/F · ShapeNet-Cars multi-view (128^3), 8 viewsmean IoU: 0.806 -> 0.819Improved
use multi-scale context-aware fusion instead of context-aware fusion (ablation)Pix2Vox++/F · ShapeNet-Cars multi-view (128^3), 8 viewsmean IoU: 0.768 -> 0.819Improved
add more input views (1 to 20) to the fusion (ablation)Pix2Vox++/A · ShapeNet multi-view (32^3)mean IoU: 0.670 -> 0.719Improved
swap ResNet50 backbone for VGG16 (pretrained) (ablation)Pix2Vox++/A · ShapeNet single-view (32^3)mean IoU: 0.670 -> 0.661Hurt
swap ResNet50 backbone for DenseNet169 (pretrained) (ablation)Pix2Vox++/A · ShapeNet single-view (32^3)mean IoU: 0.670 -> 0.669No clear effect
use pretrained backbone weights (ablation)Pix2Vox++/A · ShapeNet single-view (32^3)mean IoU: 0.669 -> 0.670Improved
train on Things3D-Chairs instead of ShapeNet-Chairs (ablation)Pix2Vox++/A · Pix3D chairs (32^3)mean IoU: 0.204 -> 0.269Improved
train on Things3D-Chairs-RfC instead of ShapeNet-Chairs-RfC (ablation)Pix2Vox++/A · Pix3D chairs (32^3)mean IoU: 0.292 -> 0.324Improved
replace multi-scale fusion with 3D conv LSTM (A-R2N2) (ablation)Pix2Vox++/A · ShapeNet multi-view (32^3)mean IoUImproved

Earlier methods this paper compares with

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