AI Paper Atlas

Research map / 3D vision / Face and shape

Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing

Garvita Tiwari, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll

ICCV 2021 · 3D vision › Face and shape · approach: Clothed human modeling · 105 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 canonical mapping network (learned blend weights) instead of nearest-neighbour SMPL weights (ablation)Neural-GIF canonical SDF · DFAUSTPoint2Surface (mm): 18.38 -> 3.28Improved
add canonical mapping network instead of nearest-neighbour SMPL weights (ablation)Neural-GIF canonical SDF · DFAUSTIoU: 0.806 -> 0.972Improved
add canonical mapping network instead of nearest-neighbour SMPL weights (ablation)Neural-GIF canonical SDF · CAPEPoint2Surface (mm): 12.93 -> 7.93Improved
add canonical mapping network instead of nearest-neighbour SMPL weights (ablation)Neural-GIF canonical SDF · ClothSeqPoint2Surface (mm): 11.89 -> 9.18Improved
add displacement field network and normal prediction on top of canonical mapping network (ablation)Neural-GIF · CAPEPoint2Surface (mm): 7.93 -> 5.86Mixed
add displacement field network and normal prediction on top of canonical mapping network (ablation)Neural-GIF · ClothSeqPoint2Surface (mm): 9.18 -> 4.73Improved
add displacement field network and normal prediction (ablation)Neural-GIF · DFAUSTPoint2Surface (mm): 3.28 -> 3.21Improved
use Neural-GIF instead of NASAimplicit clothed human model · ClothSeqIoU: 0.780 -> 0.967Improved
use Neural-GIF instead of SCANimateimplicit clothed human model · CAPEPoint2Surface (mm): 5.82 -> 5.86No clear effect
use Neural-GIF instead of SCANimateimplicit clothed human model · ClothSeqPoint2Surface (mm): 7.32 -> 4.73Improved
use Neural-GIF instead of TailorNet (template with known registration)clothing model · TailorNet skirtPoint2Surface (mm): 9.82 -> 11.14Hurt
use Neural-GIF instead of TailorNetclothing model · TailorNet shirtPoint2Surface (mm): 7.28 -> 10.98Hurt

Later papers that compared with this method

1 later accepted paper reports Neural-GIF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 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