mlsanityData to 13 Oct 2026

Mask2Restore: Self-Supervised Ultrasound Despeckling via Inpainting

arXiv 2609.32844 ↗First posted 26 Sep 2026eess.IV cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Medical ultrasound (US) is inherently degraded by speckle, a granular interference pattern that is often treated as a complex form of noise in image restoration. However, unlike random noise, US speckle originates from coherent scattering within tissue and is therefore highly spatially dependent and deterministic under fixed acquisition conditions, making US speckle suppression fundamentally different from natural image denoising. Because speckle-free US targets are unavailable in practice, self-supervised denoising is necessary. Blind-spot networks (BSN) are the dominant self-supervised paradigm for natural images, but their pixel-wise masking strategy assumes spatially independent noise, an assumption poorly matched to US speckle, which is spatially correlated over multiple pixels rather than pixel-wise independent. To address this mismatch, we propose Mask2Restore, a self-supervised US despeckling framework that reformulates despeckling as contextual inpainting with block-wise masking on single noisy images. Unlike pixel-wise BSN masking, block-wise masking addresses this multi-pixel speckle correlation by removing locally correlated speckle neighborhoods and shifting the reconstruction cues used by the network from adjacent speckle correlations to broader anatomical context. We further introduce cross-resolution context regularization (CRCR), which suppresses residual speckle bias by enforcing consistency across multi-resolution predictions. Experiments on simulated and in vivo carotid US, unseen fine-structure cases, and downstream cardiac segmentation demonstrate improved speckle-detail trade-offs, better preservation of fine anatomical structures, and practical value for subsequent image analysis.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 26 Sep 2026.

Builds on

18 of 37 references.

References · 18

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,656
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,082
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,820
  4. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,354
  5. 2017Deep Image Priorcited by 1,097
  6. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 529
  7. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 361
  8. 2019Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiographycited by 244
  9. 2021Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Imagescited by 172
  10. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 93
  11. 2022Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spotscited by 83
  12. 2022CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoisingcited by 46
6 more
  1. 2023Robotic Ultrasound Imaging: State-of-the-Art and Future Perspectivescited by 30
  2. 2023Skeleton Graph-based Ultrasound-CT Non-rigid Registrationcited by 9
  3. 2025Speckle2Self: Self-Supervised Ultrasound Speckle Reduction Without Clean Datacited by 9
  4. 2025Rotation-Equivariant Self-Supervised Method in Image Denoisingcited by 6
  5. 2024Class-Aware Cartilage Segmentation for Autonomous US-CT Registration in Robotic Intercostal Ultrasound Imagingcited by 5
  6. 2026Defining Robust Ultrasound Quality Metrics via an Ultrasound Foundation Modelcited by 1

Built on by

Not cited yet.