AI Paper Atlas

Research map / 3D vision / Face and shape

Iterative Superquadric Recomposition of 3D Objects from Multiple Views

Stephan Alaniz, Massimiliano Mancini, Zeynep Akata

ICCV 2023 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 12 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
use iterative superquadric addition instead of random simultaneous init (ablation)ISCO · ShapeNet (16 views)mean volumetric IoU: 0.578 -> 0.656Improved
use iterative addition (ablation)ISCO · ShapeNet (4 views)mean volumetric IoU: 0.493 -> 0.576Improved
use iterative addition (ablation)ISCO · ShapeNet (8 views)mean volumetric IoU: 0.557 -> 0.637Improved
increase number of views from 4 to 16 (ablation)ISCO · ShapeNetmean volumetric IoU: 0.576 -> 0.637 -> 0.656Improved
increase the number of superquadrics (ablation)ISCO · ShapeNetmean IoU: gradual improvement with diminishing returnsImproved
set lambda to 0.6 instead of 0.4 (ablation)ISCO · ShapeNet (16 views)mean volumetric IoU: 0.629 -> 0.650Improved
set lambda to 0.6 instead of 0.8 (ablation)ISCO · ShapeNet (16 views)mean volumetric IoU: 0.613 -> 0.650Improved
use multi-view ISCO instead of point-cloud NBPISCO · ShapeNetmean volumetric IoU: 0.588 -> 0.656Improved
use ISCO instead of EMSISCO · ShapeNetmean volumetric IoU: 0.330 -> 0.656Improved
use ISCO instead of implicit NeuSISCO · ShapeNetmean volumetric IoU: 0.701 -> 0.656Hurt
use ISCO instead of EMS/NBP with consistent assignmentISCO · ShapeNet-part tableper-part mIoU: 32.3 -> 70.7 (EMS), 32.9 -> 70.7 (NBP)Improved
train HSQ with 16 views instead of single viewHSQ · ShapeNetmIoU: improves slightly by 0.029; ISCO 0.656 still higherImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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