TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising

• URL: http://arxiv.org/abs/2604.04484v1
• Date: Mon, 06 Apr 2026 07:20:19 GMT
• Title: TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
• Abstract summary: Blind-spot networks (BSNs) enable self-supervised image denoising by preventing access to the target pixel.<n>We propose the Triangular-Masked Blind-Spot Network (TM-BSN), a novel blind-spot architecture that accurately models the spatial correlation of real sRGB noise.<n>Our method achieves state-of-the-art performance, significantly outperforming existing self-supervised approaches.
• Score: 22.77487319845247
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Blind-spot networks (BSNs) enable self-supervised image denoising by preventing access to the target pixel, allowing clean signal estimation without ground-truth supervision. However, this approach assumes pixel-wise noise independence, which is violated in real-world sRGB images due to spatially correlated noise from the camera's image signal processing (ISP) pipeline. While several methods employ downsampling to decorrelate noise, they alter noise statistics and limit the network's ability to utilize full contextual information. In this paper, we propose the Triangular-Masked Blind-Spot Network (TM-BSN), a novel blind-spot architecture that accurately models the spatial correlation of real sRGB noise. This correlation originates from demosaicing, where each pixel is reconstructed from neighboring samples with spatially decaying weights, resulting in a diamond-shaped pattern. To align the receptive field with this geometry, we introduce a triangular-masked convolution that restricts the kernel to its upper-triangular region, creating a diamond-shaped blind spot at the original resolution. This design excludes correlated pixels while fully leveraging uncorrelated context, eliminating the need for downsampling or post-processing. Furthermore, we use knowledge distillation to transfer complementary knowledge from multiple blind-spot predictions into a lightweight U-Net, improving both accuracy and efficiency. Extensive experiments on real-world benchmarks demonstrate that our method achieves state-of-the-art performance, significantly outperforming existing self-supervised approaches. Our code is available at https://github.com/parkjun210/TM-BSN.

Related papers

• Compressive sensing inspired self-supervised single-pixel imaging [48.79613794195208]
  SISTA-Net is a compressive sensing-inspired self-supervised method for single-pixel imaging.<n>We leverage deep nonlinear networks as adaptive sparse transforms combined with a learnable soft-thresholding operator to impose explicit physical sparsity in the latent domain.<n>Experiments on multiple simulation scenarios demonstrate that SISTA-Net outperforms state-of-the-art methods by 2.6 dB in PSNR.
  arXiv  Detail & Related papers  (2026-03-31T13:31:43Z)
• N-BVH: Neural ray queries with bounding volume hierarchies [51.430495562430565]
  In 3D computer graphics, the bulk of a scene's memory usage is due to polygons and textures. We devise N-BVH, a neural compression architecture designed to answer arbitrary ray queries in 3D. Our method provides faithful approximations of visibility, depth, and appearance attributes.
  arXiv  Detail & Related papers  (2024-05-25T13:54:34Z)
• ASCNet: Asymmetric Sampling Correction Network for Infrared Image Destriping [25.816984064145906]
  We propose a novel infrared image destriping method called Asymmetric Sampling Correction Network (ASCNet)<n>Our ASCNet consists of three core elements: Residual Haar Discrete Wavelet Transform (RHDWT), Pixel Shuffle (PS), and Column Non-uniformity Correction Module (CNCM)
  arXiv  Detail & Related papers  (2024-01-28T06:23:55Z)
• Self-supervised Image Denoising with Downsampled Invariance Loss and Conditional Blind-Spot Network [12.478287906337194]
  Most representative self-supervised denoisers are based on blind-spot networks. A standard blind-spot network fails to reduce real camera noise due to the pixel-wise correlation of noise. We propose a novel self-supervised training framework that can remove real noise.
  arXiv  Detail & Related papers  (2023-04-19T08:55:27Z)
• Exploring Efficient Asymmetric Blind-Spots for Self-Supervised Denoising in Real-World Scenarios [44.31657750561106]
  Noise in real-world scenarios is often spatially correlated, which causes many self-supervised algorithms to perform poorly. We propose Asymmetric Tunable Blind-Spot Network (AT-BSN), where the blind-spot size can be freely adjusted. We show that our method achieves state-of-the-art, and is superior to other self-supervised algorithms in terms of computational overhead and visual effects.
  arXiv  Detail & Related papers  (2023-03-29T15:19:01Z)
• Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising [73.71324390085714]
  We propose a novel perspective to solve the problem of real-world sRGB image denoising. We take into account the respective characteristics of flat and textured regions in noisy images, and construct supervisions for them separately. We present a locally aware network (LAN) to meet the requirement, while LAN itself is supervised with the output of BNN.
  arXiv  Detail & Related papers  (2023-03-27T06:18:20Z)
• I2V: Towards Texture-Aware Self-Supervised Blind Denoising using Self-Residual Learning for Real-World Images [8.763680382529412]
  pixel-shuffle downsampling (PD) has been proposed to eliminate the spatial correlation of noise. We propose self-residual learning without the PD process to maintain texture information. The results of extensive experiments show that the proposed method outperforms state-of-the-art self-supervised blind denoising approaches.
  arXiv  Detail & Related papers  (2023-02-21T08:51:17Z)
• AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network [60.650035708621786]
  Blind-spot network (BSN) and its variants have made significant advances in self-supervised denoising. It is challenging to deal with spatially correlated real-world noise using self-supervised BSN. Recently, pixel-shuffle downsampling (PD) has been proposed to remove the spatial correlation of real-world noise. We propose an Asymmetric PD (AP) to address this issue, which introduces different PD stride factors for training and inference.
  arXiv  Detail & Related papers  (2022-03-22T15:04:37Z)
• Hyperspectral Image Super-resolution via Deep Progressive Zero-centric Residual Learning [62.52242684874278]
  Cross-modality distribution of spatial and spectral information makes the problem challenging. We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net. Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
  arXiv  Detail & Related papers  (2020-06-18T06:32:11Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)
• Spatial-Adaptive Network for Single Image Denoising [14.643663950015334]
  We propose a novel spatial-adaptive denoising network (SADNet) for efficient single image blind noise removal. Our method can surpass the state-of-the-art denoising methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2020-01-28T12:24:17Z)

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.