A new self-supervised denoising framework, Log-Domain Noisier2Inverse, has been developed and evaluated for inertial confinement fusion (ICF) images affected by multiplicative uniform noise. The framework demonstrates significant improvements, achieving a mean PSNR of 21.41 dB and an SSIM of 0.8358, which is a substantial gain over the noisy input. This method substantially outperforms existing techniques like BM3D and Noise2Self in denoising ICF imagery, while also being entirely self-supervised during training. AI
IMPACT This research offers a novel self-supervised approach for image denoising in specialized scientific fields, potentially improving data quality for analysis.
RANK_REASON The cluster contains an academic paper detailing a new framework and its evaluation.
- arXiv
- Block-matching and 3D filtering
- inertial confinement fusion
- Log-Domain Noisier2Inverse
- Noise2Self
- peak signal-to-noise ratio
- Structural Similarity Index Measure
- Uniform noise
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
