paper-with-me

홈 › Papers

LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models

2023-12-02 · Qiang Wen, Zhefan Rao, Yazhou Xing, Qifeng Chen

Enhancing a low-light noisy RAW image into a well-exposed and clean sRGB image is a significant challenge for modern digital cameras. Prior approaches have difficulties in recovering fine-grained details and true colors of the scene under extremely low-light environments due to near-to-zero SNR. Meanwhile, diffusion models have shown significant progress towards general domain image generation. In this paper, we propose to leverage the pre-trained latent diffusion model to perform the neural ISP for enhancing extremely low-light images. Specifically, to tailor the pre-trained latent diffusion model to operate on the RAW domain, we train a set of lightweight taming modules to inject the RAW information into the diffusion denoising process via modulating the intermediate features of UNet. We further observe different roles of UNet denoising and decoder reconstruction in the latent diffusion model, which inspires us to decompose the low-light image enhancement task into latent-space low-frequency content generation and decoding-phase high-frequency detail maintenance. Through extensive experiments on representative datasets, we demonstrate our simple design not only achieves state-of-the-art performance in quantitative evaluations but also shows significant superiority in visual comparisons over strong baselines, which highlight the effectiveness of powerful generative priors for neural ISP under extremely low-light environments. The project page is available at https://csqiangwen.github.io/projects/ldm-isp/

📄 PDF Abstract BibTeX arXiv:2312.01027

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderDenoisingImage EnhancementImage GenerationLow-Light Image Enhancement

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Latent Diffusion Model Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Boosting Fidelity for Pre-Trained-Diffusion-Based Low-Light Image Enhancement via Condition Refinement

2025-10-20 · Xiaogang Xu, Jian Wang, Yunfan Lu, Ruihang Chu 외 arxiv

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) metho…

Low-Light Image Enhancement

Discrete Wavelet Transform as a Facilitator for Expressive Latent Space Representation in Variational Autoencoders in Satellite Imagery

2025-10-01 · Arpan Mahara, Md Rezaul Karim Khan, Naphtali Rishe, Wenjia Wang 외 arxiv

Latent Diffusion Models (LDM), a subclass of diffusion models, mitigate the computational complexity of pixel-space diffusion by operating within a compressed latent space constructed by Variational Autoencoders (VAEs), …

LightCtrl: Training-free Controllable Video Relighting

2026-03-28 · Yizuo Peng, Xuelin Chen, Kai Zhang, Xiaodong Cun arxiv

Recent diffusion models have achieved remarkable success in image relighting, and this success has quickly been extended to video relighting. However, existing methods offer limited explicit control over illumination in …

Image Relighting

LatentSpeech: Latent Diffusion for Text-To-Speech Generation

2024-12-11 · Haowei Lou, Helen Paik, Pari Delir Haghighi, Wen Hu 외

Diffusion-based Generative AI gains significant attention for its superior performance over other generative techniques like Generative Adversarial Networks and Variational Autoencoders. While it has achieved notable adv…

text-to-speechText to Speech

AP-LDM: Attentive and Progressive Latent Diffusion Model for Training-Free High-Resolution Image Generation

2024-10-08 · Boyuan Cao, Jiaxin Ye, Yujie Wei, Hongming Shan

Latent diffusion models (LDMs), such as Stable Diffusion, often experience significant structural distortions when directly generating high-resolution (HR) images that exceed their original training resolutions. A straig…

DenoisingImage Generation