{"ID":2825212,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.21637","arxiv_id":"2512.21637","title":"Training-Free Disentangled Text-Guided Image Editing via Sparse Latent Constraints","abstract":"Text-driven image manipulation often suffers from attribute entanglement, where modifying a target attribute (e.g., adding bangs) unintentionally alters other semantic properties such as identity or appearance. The Predict, Prevent, and Evaluate (PPE) framework addresses this issue by leveraging pre-trained vision-language models for disentangled editing. In this work, we analyze the PPE framework, focusing on its architectural components, including BERT-based attribute prediction and StyleGAN2-based image generation on the CelebA-HQ dataset. Through empirical analysis, we identify a limitation in the original regularization strategy, where latent updates remain dense and prone to semantic leakage. To mitigate this issue, we introduce a sparsity-based constraint using L1 regularization on latent space manipulation. Experimental results demonstrate that the proposed approach enforces more focused and controlled edits, effectively reducing unintended changes in non-target attributes while preserving facial identity.","short_abstract":"Text-driven image manipulation often suffers from attribute entanglement, where modifying a target attribute (e.g., adding bangs) unintentionally alters other semantic properties such as identity or appearance. The Predict, Prevent, and Evaluate (PPE) framework addresses this issue by leveraging pre-trained vision-lang...","url_abs":"https://arxiv.org/abs/2512.21637","url_pdf":"https://arxiv.org/pdf/2512.21637v1","authors":"[\"Mutiara Shabrina\",\"Nova Kurnia Putri\",\"Jefri Satria Ferdiansyah\",\"Sabita Khansa Dewi\",\"Novanto Yudistira\"]","published":"2025-12-25T11:38:10Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\",\"Generative Adversarial Network\"]","has_code":false}