Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement
- URL: http://arxiv.org/abs/2510.17105v1
- Date: Mon, 20 Oct 2025 02:40:06 GMT
- Title: Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement
- Authors: Xiaogang Xu, Jian Wang, Yunfan Lu, Ruihang Chu, Ruixing Wang, Jiafei Wu, Bei Yu, Liang Lin,
- Abstract summary: Pre-Trained Diffusion-Based (PTDB) methods often sacrifice content fidelity to attain higher perceptual realism.<n>We propose a novel optimization strategy for conditioning in pre-trained diffusion models, enhancing fidelity while preserving realism and aesthetics.<n>Our approach is plug-and-play, seamlessly integrating into existing diffusion networks to provide more effective control.
- Score: 63.54516423266521
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Diffusion Once and Done: Degradation-Aware LoRA for Efficient All-in-One Image Restoration [14.922600858354983]
Diffusion Once and Done (DOD) method aims to achieve superior restoration performance with only one-step sampling of Stable Diffusion (SD) models.<n>Our method outperforms existing diffusion-based restoration approaches in both visual quality and inference efficiency.
arXiv Detail & Related papers (2025-08-05T12:26:28Z) - Enhanced DACER Algorithm with High Diffusion Efficiency [30.13489573844592]
We propose DACERv2, which exploits a Q-gradient field objective to guide the denoising process at each diffusion step.<n>We show that DACERv2 achieves higher performance in most complex control environments with only five diffusion steps and shows greater multimodality.
arXiv Detail & Related papers (2025-05-29T13:21:58Z) - Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility [62.272571285823595]
We show how immiscibility eases denoising and improves efficiency.<n>We propose a family of implementations including K-nearest neighbor (KNN) noise selection and image scaling to reduce miscibility.<n>This work establishes a potentially new direction for future research into high-efficiency diffusion training.
arXiv Detail & Related papers (2025-05-24T05:38:35Z) - One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
arXiv Detail & Related papers (2025-03-09T09:39:57Z) - Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs [36.65594293655289]
DoSSR is a Domain Shift diffusion-based SR model that capitalizes on the generative powers of pretrained diffusion models.<n>At the core of our approach is a domain shift equation that integrates seamlessly with existing diffusion models.<n>Our proposed method achieves state-of-the-art performance on synthetic and real-world datasets, while notably requiring only 5 sampling steps.
arXiv Detail & Related papers (2024-09-26T12:16:11Z) - Digging into contrastive learning for robust depth estimation with diffusion models [55.62276027922499]
We propose a novel robust depth estimation method called D4RD.
It features a custom contrastive learning mode tailored for diffusion models to mitigate performance degradation in complex environments.
In experiments, D4RD surpasses existing state-of-the-art solutions on synthetic corruption datasets and real-world weather conditions.
arXiv Detail & Related papers (2024-04-15T14:29:47Z) - Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration.
We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
arXiv Detail & Related papers (2023-06-01T03:08:28Z) - Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution.
By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
arXiv Detail & Related papers (2023-05-11T17:55:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.