AI Paper Atlas

Research map / 3D vision / Face and shape

Totems: Physical Objects for Verifying Visual Integrity

Jingwei Ma, Lucy Chai, Minyoung Huh, Tongzhou Wang, Ser-Nam Lim, Phillip Isola, Antonio Torralba

ECCV 2022 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction · 3 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 joint totem position optimization (ablation)totem reconstruction · Real imagesReconstruction L1: 0.149 -> 0.109Improved
add joint totem position optimization (ablation)totem reconstruction · Synthetic Env map sceneReconstruction L1: 0.173 -> 0.103Improved
add joint totem position optimization (ablation)totem reconstruction · Synthetic Box sceneReconstruction L1: 0.057 -> 0.054Improved
add joint totem position optimization (ablation)totem reconstruction · Synthetic Box scenePose L1: 0.008 -> 0.108Hurt
add joint totem position optimization (ablation)totem reconstruction · Synthetic Env map scenePose L1: 0.060 -> 0.027Improved
use ground-truth oracle totem positions instead of estimated (ablation)totem reconstruction · Synthetic Env map sceneReconstruction L1: 0.103 -> 0.040Improved
add totem optimization to detector (L1 score) (ablation)totem detection · CAFpatch-wise mAP: 0.485 -> 0.554Improved
add totem optimization to detector (LPIPS score) (ablation)totem detection · Splicepatch-wise mAP: 0.449 -> 0.739Improved
add totem optimization to detector (LPIPS score) (ablation)totem detection · Colorpatch-wise mAP: 0.954 -> 0.946No clear effect
use totem-based method instead of ManTra-Nettotem detection with LPIPS · CAFpatch-wise mAP: 0.181 -> 0.666Improved
use LPIPS instead of L1 as patch score (ablation)totem detection with totem opt. · Splicepatch-wise mAP: 0.638 -> 0.739Improved
increase number of totems from two to four (ablation)totem reconstruction · Synthetic scenereconstruction L1: 0.16 -> 0.08Improved

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