AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Cross-modal Latent Space Alignment for Image to Avatar Translation

Manuel Ladron de Guevara, Jose Echevarria, Yijun Li, Yannick Hold-Geoffroy, Cameron Smith, Daichi Ito

ICCV 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 4 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 parametric cross-modal avatar generation instead of image-to-image GAN baselinesAvatar generation · Held-out avatarsL1: 0.2059 -> 0.1864Improved
use proposed method instead of U-GAT-IT in user studyAvatar generation · User study qualitypreference %: 99.1%Improved
add cross-modal alignment losses (ablation)Mapping network F · Held-out avatarsLPIPS: 0.1876 -> 0.1835Improved
add weight alignment loss (ablation)Mapping network F · Held-out avatarsLPIPS: 0.1852 -> 0.1835Improved
add MSE alignment term (ablation)Mapping network F · Held-out avatarsL1: 0.1841 -> 0.1832No clear effect
add weight alignment loss (ablation)Mapping network F · Held-out avatarsL1: 0.1833 -> 0.1832No clear effect
train mapping with fewer than 3000 paired samples (ablation)Mapping network F · Qualitative (Figure 8)identity and avatar qualityHurt
train with 3995 pairs instead of 9970 (ablation)Mapping network F · Qualitative (Figure 8)identity preservationNo clear effect

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