{"ID":2852526,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.17105","arxiv_id":"2510.17105","title":"Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement","abstract":"Diffusion-based methods, leveraging pre-trained large models like Stable Diffusion via ControlNet, have achieved remarkable performance in several low-level vision tasks. However, Pre-Trained Diffusion-Based (PTDB) methods often sacrifice content fidelity to attain higher perceptual realism. This issue is exacerbated in low-light scenarios, where severely degraded information caused by the darkness limits effective control. We identify two primary causes of fidelity loss: the absence of suitable conditional latent modeling and the lack of bidirectional interaction between the conditional latent and noisy latent in the diffusion process. To address this, we propose a novel optimization strategy for conditioning in pre-trained diffusion models, enhancing fidelity while preserving realism and aesthetics. Our method introduces a mechanism to recover spatial details lost during VAE encoding, i.e., a latent refinement pipeline incorporating generative priors. Additionally, the refined latent condition interacts dynamically with the noisy latent, leading to improved restoration performance. Our approach is plug-and-play, seamlessly integrating into existing diffusion networks to provide more effective control. Extensive experiments demonstrate significant fidelity improvements in PTDB methods.","short_abstract":"Diffusion-based methods, leveraging pre-trained large models like Stable Diffusion via ControlNet, have achieved remarkable performance in several low-level vision tasks. However, Pre-Trained Diffusion-Based (PTDB) methods often sacrifice content fidelity to attain higher perceptual realism. This issue is exacerbated i...","url_abs":"https://arxiv.org/abs/2510.17105","url_pdf":"https://arxiv.org/pdf/2510.17105v1","authors":"[\"Xiaogang Xu\",\"Jian Wang\",\"Yunfan Lu\",\"Ruihang Chu\",\"Ruixing Wang\",\"Jiafei Wu\",\"Bei Yu\",\"Liang Lin\"]","published":"2025-10-20T02:40:06Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Variational Autoencoder\"]","has_code":false}