AI Paper Atlas

Research map / 3D vision / Face and shape

3D-Aware Semantic-Guided Generative Model for Human Synthesis

Jichao Zhang, Enver Sangineto, Hao Tang, Aliaksandr Siarohin, Zhun Zhong, Nicu Sebe, Wei Wang

ECCV 2022 · 3D vision › Face and shape · approach: Generative textures for 3D humans · 25 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
use semantic-mask-guided 3D-SGAN instead of GIRAFFE3D-aware human GAN · DeepFashion RandomFID: 42.73 -> 8.240Improved
use 3D-SGAN instead of GIRAFFE3D-aware human GAN · VITONFID: 26.750 -> 14.060Improved
use 3D-SGAN instead of ShadeGAN3D-aware human GAN · DeepFashion RotationaMP: 89.0 -> 81.0Hurt
use 3D-SGAN instead of CIPS-3D3D-aware human GAN · DeepFashion TextureFID: 36.16 -> 60.63Hurt
add semantic consistency loss l_ss (ablation)3D-SGAN · DeepFashion consistencyL1 silhouette distance: 5.2489 -> 3.9614Improved
add pose-semantic consistency loss l_ps (ablation)3D-SGAN · DeepFashion pose consistencyLPIPS diversity: 0.1132 -> 0.0393Improved
use GNeRF 3D generator instead of vanilla 2D GAN (ablation)3D-SGAN · DeepFashionFID: 13.24 -> 8.240Improved
add semantic masks as intermediate representation (ablation)3D-SGAN · DeepFashionFID: 66.79 -> 8.240Improved
add VAE-conditioned texture generator (ablation)3D-SGAN · DeepFashionFID: 14.35 -> 8.240Improved
train G3D and Gt jointly instead of separately (ablation)3D-SGAN · DeepFashionFIDHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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