AI Paper Atlas

Research map / 3D vision / Face and shape

Deep Mesh Reconstruction From Single RGB Images via Topology Modification Networks

Junyi Pan, Xiaoguang Han, Weikai Chen, Jiapeng Tang, Kui Jia

ICCV 2019 · 3D vision › Face and shape · approach: Single-view 3D reconstruction · 202 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 topology modification (face pruning) and boundary refinement to the baseline (ablation)Baseline mesh deformation · ShapeNet 5 categories meanCD (x1e-3): 2.930 -> 2.277Improved
add topology modification and boundary refinement to the baseline (ablation)Baseline mesh deformation · ShapeNet 5 categories meanEMD (x1e-2): 10.360 -> 9.059Improved
add topology modification and boundary refinement (ablation)Baseline · ShapeNet chairCD (x1e-3): 4.325 -> 3.064Improved
add topology modification and boundary refinement (ablation)Baseline · ShapeNet tableCD (x1e-3): 4.798 -> 3.616Improved
add topology modification and boundary refinement (ablation)Baseline · ShapeNet planeCD (x1e-3): 1.433 -> 1.390No clear effect
add topology modification and boundary refinement (ablation)Baseline · ShapeNet firearmCD (x1e-3): 1.145 -> 1.142No clear effect
use the proposed method instead of AtlasNet-25 before PSR on single-view reconstructionAtlasNet-25 · ShapeNet meanCD (x1e-3): 2.747 -> 2.277Improved
apply Poisson surface reconstruction to closed meshes, proposed vs AtlasNet-25AtlasNet-25 (PSR) · ShapeNet chair (20 shapes)CD: 3.430 -> 2.304Improved
use the proposed method instead of AtlasNet-25 for autoencodingAtlasNet-25 (AE) · ShapeNet autoencodingCD: 0.765 -> 0.655Improved
use the proposed method instead of AtlasNet-25 for autoencodingAtlasNet-25 (AE) · ShapeNet autoencodingEMD: 8.467 -> 6.754Improved
add progressive shaping (keep the first subnet) before face pruning (ablation)Ours · ShapeNetqualitative mesh qualityImproved
use unit square instead of sphere as initial mesh (ablation)Ours · ShapeNetqualitative mesh qualityNo clear effect

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