The paper presents a real‑time on‑device system for editing the emotional intensity of visual content. Using a MobileNetV4 backbone with FiLM‑based conditioning, the model predicts parameters for differentiable global transformations in a single 3.7 ms forward pass, replacing 80‑second per‑image optimization. A user study with 54 participants showed reduced viewer arousal and higher perceived quality compared to a grayscale filter, and the system runs at 60 fps on a Samsung Galaxy S23.
By Musa Rochi, Marcel Schubert, Christoph Gebhardt
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.
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.
By Xingzu Zhan, Lin Gu, Ruogu Fang
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
arXiv:2606. 09901v1 Announce Type: cross Abstract: Diffusion-based generative models enable powerful image editing capabilities, but achieving precise control while maintaining fidelity and safety remains challenging.
By Yi Hu, Leying Yi, Emily Davis, Finn Carter
KwaiMind is a commercial image editing system that combines general editing capabilities with e-commerce specialization. It uses an agent-based data engine with 1.8 million editing pairs and a multimodal diffusion transformer trained through pre‑training, fine‑tuning, preference optimization, and online reinforcement learning. The system is guided by a vision‑language judge and specialized rewards for click‑through rate, text rendering, and product consistency, and it achieves top scores on ImgEdit, GEdit, REDEdit, and the new Ecom‑Bench, while improving predicted and actual CTR in offline and online experiments.
By Junlong Wu, Zijun Li, Yuting Hu, Jia Sun, Pengcheng Wei, Yimin Zhou, Honglie Wang, Huaiqing Wang, Dewen Fan, Fei Zuo, Haixuan Gao, Lihui Peng, Tingxuan She, Yuqing Li, Boheng Zhang, Fan Yang, Wenwu Ou
arXiv:2609.24215v1 Announce Type: new
Abstract: Although text-to-image models can accurately depict subjects and scenes, creators still struggle to specify the fine-grained emotions an image should c...
By Minglang Li, Yueyue Fang, Xieping Gao
arXiv:2605. 31162v1 Announce Type: cross Abstract: Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored.
By Shreyansh Modi, Akshat Tomar, Aarush Aggarwal
arXiv:2608.28802v1 Announce Type: cross
Abstract: Facial appearance editing powers popular applications like FaceApp and Photoshop. Generative Adversarial Networks (GANs) and 3D Morphable Models (3DM...
By Rahul Nair, Saurav Pandit, Hannah Kerner
The paper introduces the Mult2EMo dataset, which gathers annotations from both authors and readers on multimodal social media posts and the real‑world events that triggered them. It investigates how well readers can reconstruct the authors’ emotional experience from the post content, emphasizing the importance of both text and image modalities. The study finds that accurate emotion reconstruction is possible but remains challenging, especially when images dominate the expression and when understanding the triggering event is essential.
By Christopher Bagdon, Carina Silberer, Roman Klinger
arXiv:2606. 13247v1 Announce Type: new Abstract: Text-to-image diffusion models have achieved impressive results in synthesizing high-quality images from natural language prompts.
By Emna Othmen, Mohamed Yassine Landolsi, Lotfi Ben Romdhane
Unified models trained for both instruction-based image editing and text-to-image generation typically keep source-image conditioning throughout denoising. This study shows that for some edits, source attention naturally decreases during sampling, suggesting that switching to text-to-image conditioning for short intervals can improve edit quality without sacrificing perceptual preservation. Across three editors and four benchmarks, task switching balances quality and preservation, demonstrating that unified editors benefit from using both conditioning modes they are trained for.
By Lidia Troeshestova, Alexander Ustyuzhanin, Sergey Kastryulin