arXiv:2608.28823v1 Announce Type: cross
Abstract: Artists coordinate human pose, illumination, and camera placement to convey narrative and emotion, but existing generative methods typically model th...
By Yunge Wen
arXiv:2608.22329v1 Announce Type: cross
Abstract: Emotion-aware artistic image generation requires a model to satisfy semantic content, artistic style, and target emotion simultaneously. The key chal...
By Qianqian Tang, Jiayi Gao, Ting Lei, Yang Liu
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:2606. 09846v1 Announce Type: cross Abstract: Visual art remains largely inaccessible to blind and low-vision (BLV) audiences due to brief or absent alt-text, which rarely conveys the sensory, spatial, or emotional qualities of an artwork.
By Vignesh Nagarajan
Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions.
CogCanvas is a new benchmark for multi-subject reference-based image generation, featuring 1,952 curated reference images of 100 celebrities, 115 objects/fashion items, and 29 real-world backgrounds. It generates 1,361 compositional prompts with 2–5 people, using a pipeline that includes DINOv2 deduplication, aesthetic filtering, and automated graph derivation for interaction and positioning. The benchmark evaluates three tasks—reference-based multi-human-object generation, text-to-image compositional generation, and reference retrieval—under a six-axis protocol, and introduces BG‑Sim and Attr‑VQA metrics to assess background fidelity and attribute binding.
By Long-Bao Nguyen, Quang-Khai Le, Tam V. Nguyen, Minh-Triet Tran, Trung-Nghia Le