YOND: Practical Blind Raw Image Denoising Free from Camera-Specific Data Dependency

Hansen Feng, Lizhi Wang, Yiqi Huang, Tong Li, Lin Zhu, Hua Huang

(Under Review)

Paper (Comming Soon)

• We introduce a novel blind raw image denoising method. With our method, an AWGN denoiser can generalize to various real raw data with a single training on synthetic datasets. We name our method YOND, as you need nothing else under our method, You Only Need a Denoiser.
• YOND consists of three key modules: the coarse-to-fine noise estimation (CNE), the expectation-matched variance-stabilizing transform (EM-VST), and the SNR-guided denoiser (SNR-Net).
• Extensive experiments across diverse camera datasets, along with flexible solutions for challenging cases, demonstrate the practicality of YOND.

Physics-guided Noise Neural Proxy for Practical Low-light Raw Image Denoising

Hansen Feng, Lizhi Wang, Yiqi Huang, Yuzhi Wang, Lin Zhu, Hua Huang

(Under Major Revision)

Paper | Code (Eval Only) | Project | Results & Checkpoints

• In this paper, we propose a novel strategy: learning the noise model from dark frames instead of paired real data.
• Based on the proposed strategy, we introduce an efficient Physics-guided Noise Neural Proxy (PNNP) to approximate the real-world sensor noise model.
• The low data dependency of PNNP exhibits its powerful potential for practical low-light raw image denoising.

Stimulating the Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling

Tong Li, Hansen Feng, Lizhi Wang, Lin Zhu, Zhiwei Xiong, Hua Huang

TPAMI, 2024

Paper | Code | Chinese Note

• We present a novel strategy called the Diffusion Model for Image Denoising (DMID) by understanding and rethinking the diffusion model from a denoising perspective.
• Our DMID strategy includes an adaptive embedding method that embeds the noisy image into a pre-trained unconditional diffusion model and an adaptive ensembling method that reduces distortion in the denoised image.

Learnability Enhancement for Low-light Raw Denoising: A Data Perspective

Hansen Feng, Lizhi Wang, Yuzhi Wang, Haoqiang Fan, Hua Huang

TPAMI, 2023

Paper | Code | Project | Chinese Note | Dataset

• The limited data volume, complicated noise model, and underdeveloped data quality have constituted the learnability bottleneck of the data mapping between paired real data, which limits the performance of the learning-based method.
• To break through the bottleneck, we introduce a learnability enhancement strategy including three efficient methods: shot noise augmentation (SNA), dark shading correction (DSC), and a developed image acquisition protocol with corresponding Low-light Raw Image Denoising (LRID) dataset.

Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling

ACMMM, 2022 (Best Paper Runner-Up Award)

Hansen Feng, Lizhi Wang, Yuzhi Wang, Hua Huang

Paper | Code | Project | Chinese Note | Video

• We present a learnability enhancement strategy to reform paired real data according to noise modeling (PMN).