AI Paper Atlas

Research map / 3D vision / Face and shape

LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction

Mohammad Samiul Arshad, William J. Beksi

ICCV 2023 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 7 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 probabilistic occupancy and occupancy loss (ablation)LIST Base · ShapeNet 5 classesCD (x1e-3): 11.35 -> 9.64Improved
use a single encoder for coarse prediction and query localization (ablation)LIST · ShapeNet 5 classesCD (x1e-3): 9.64 -> 10.72Hurt
use separate encoders and fuse features rather than add two decoder predictions (ablation)LIST 2D · ShapeNet 5 classesCD (x1e-3): 8.48 -> 7.32Improved
use learned localization module instead of estimated camera parameters (ablation)LIST · ShapeNet 5 classesCD (x1e-3): 7.89 -> 7.32Improved
LIST vs D2IM-Net on occluded surfacesLIST · ShapeNet 5 classes, occluded surfacesCD_os (x1e-3): 19.43 -> 15.67Improved
LIST vs IM3D on real Pix3D imagesLIST · Pix3DCD (x1e-3): 6.72 -> 4.36Improved
use ground-truth camera data instead of estimated for baselinesD2IM-Net style baselines · ShapeNetreconstruction qualityImproved

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