AI Paper Atlas

Research map / 3D vision / Face and shape

Coupling Explicit and Implicit Surface Representations for Generative 3D Modeling

Omid Poursaeed, Matthew Fisher, Noam Aigerman, Vladimir G. Kim

ECCV 2020 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 35 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
couple explicit AtlasNet and implicit OccupancyNet with consistency losses (AN branch)AtlasNet · Single-view reconstructionChamfer-L1: 1.74 -> 1.60Improved
couple explicit AtlasNet and implicit OccupancyNet (ON branch)OccupancyNet · Single-view reconstructionChamfer-L1: 1.92 -> 1.65Improved
hybrid training (AN branch)AtlasNet · Single-view reconstructionNormal consistency: 81.8 -> 84.9Improved
hybrid training (AN branch)AtlasNet · Point cloud auto-encodingChamfer-L1: 0.58 -> 0.46Improved
hybrid training (ON branch)OccupancyNet · Point cloud auto-encodingChamfer-L1: 0.45 -> 0.41Improved
hybrid training (AN branch)AtlasNet · Point cloud auto-encodingNormal consistency: 85.4 -> 88.3Improved
hybrid training (ON branch)OccupancyNet · Point cloud auto-encodingNormal consistency: 89.8 -> 90.2Improved
add image loss L_img (ablation)Hybrid AN · Single-view reconstructionChamfer-L1: 1.64 -> 1.60Improved
add image loss L_img (ablation)Hybrid AN · Point cloud auto-encodingChamfer-L1: 0.49 -> 0.46Improved
add normal consistency loss L_norm (ablation)Hybrid AN · Single-view reconstructionNormal consistency: 83.9 -> 84.9Improved
add normal consistency loss L_norm (ablation)Hybrid AN · Point cloud auto-encodingNormal consistency: 87.6 -> 88.3Improved
add level-set consistency loss alone (no L_img, L_norm) (ablation)Hybrid AN · Single-view reconstructionChamfer-L1: 1.74 -> 1.68Improved

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