← Back to all news
arXiv Computer Vision By Xingzu Zhan, Lin Gu, Ruogu Fang

AffectDelta: Beyond Emotion Labels for Image Editing

Read the original on arXiv Computer Vision →

AffectDelta is a new image editing framework that moves beyond single emotion labels by modeling edits as transitions between eight‑dimensional emotion distributions. It uses a frozen Emotion Distribution Predictor to estimate the source state and a signed difference vector to encode the desired change, which is then translated into context‑dependent semantic and appearance modifications via a transition encoder and a diffusion backbone. The authors introduce AffectPair‑249K, a dataset of 248,841 source‑target pairs covering both cross‑category and within‑category transitions, and show that AffectDelta outperforms six baselines in affective alignment and content preservation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

Hugging Face Trending Papers
Sep 2

AffectDelta: Beyond Emotion Labels for Image Editing

AffectDelta is a new image editing framework that moves beyond single emotion labels by modeling edits as transitions between eight‑dimensional emotion distributions. It uses a frozen Emotion Distribution Predictor to estimate the source image’s affective state and encodes the signed difference to guide a diffusion backbone that applies context‑dependent semantic and appearance changes. The authors created a large AffectPair‑249K dataset of source‑target pairs and show that AffectDelta outperforms six baselines in both affective alignment and content preservation, with ablation studies supporting their design choices.

diffusionsafety
More like this →
arXiv Computer Vision
Oct 12

What We Talk About When We Talk About Emotion Editing

The paper introduces ROI‑ReFT, a method for emotional image editing that leverages neural representations from fMRI encoding models to guide visual changes while preserving content. By combining source visual responses with predicted affective changes, the approach achieves high target‑emotion accuracy (91.75%) and joint success (83.25%) on a curated set of 400 editing requests. The authors plan to release their code and dataset publicly.

By Xingzu Zhan, Lin Gu, Ruogu Fang
More like this →