arXiv Computer Vision September 25, 2026 By Cristian Comellas, Julia Navarro, Antoni Buades

A Study of the Limits of Collaborative DCT-Based Image Denoising via Interpretable Neural Networks

Read the original on arXiv Computer Vision →

The paper introduces DeepBM3D, a fully differentiable neural network that emulates the collaborative filtering strategy of BM3D for image denoising. It integrates non‑local patch grouping, DCT‑domain filtering with learned Wiener weights, and multi‑stage refinement, guided by lightweight convolutional feature extractors. Experiments demonstrate that DeepBM3D outperforms classical and hybrid baselines, competes with FFDNet at low to moderate noise levels, and excels on images with repetitive textures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

safety

arXiv AI

Jul 31

PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for Low-dose CT imaging

arXiv:2602. 21987v3 Announce Type: replace-cross Abstract: Low-dose CT images are essential for reducing radiation exposure in cancer screening, pediatric imaging, and longitudinal monitoring protocols, but their quality is often degraded by noise from low-dose acquisition, patient motion, or scanner limitations, affecting both clinical interpretation and downstream analysis.

By Jitindra Fartiyal, Pedro Freire, Sergei K. Turitsyn, Sergei G. Solovski

llms diffusion fine-tuning benchmarks

arXiv Machine Learning

Sep 16

A deep dictionary network-based foundation model for ultra-low-dose CT denoising

The paper introduces a deep dictionary network (DDN) foundation model designed for ultra‑low‑dose CT (ULDCT) denoising across multiple organs. By cascading convolutional sparse coding layers with iterative soft‑thresholding, the architecture offers inherent interpretability, while dynamic dictionary and threshold modules enhance representation. The model is pre‑trained on over one million normal‑dose CT images and fine‑tuned on multi‑organ ULDCT datasets, achieving state‑of‑the‑art performance that consistently outperforms existing methods.

By Baoshun Shi, Shuangyi Yang, Ke Jiang, Bin Zhu, Zhanli Hu, Huazhu Fu

fine-tuning safety

arXiv Computer Vision

Sep 22

PixelDiT2: Representation-Grounded Pixel Diffusion Transformers

arXiv:2609.24919v1 Announce Type: new Abstract: Recent advances in pixel-space diffusion models have narrowed the image quality gap with latent-space diffusion, but still converge more slowly and lag...

By Yongsheng Yu, Wei Xiong, Yichen Sheng, Shiqiu Liu, Jiebo Luo

llms diffusion

arXiv AI

Jul 7

Pooling-Based Context Modeling for Convolution-Free Deep Image Prior

arXiv:2607. 02952v1 Announce Type: cross Abstract: Convolutional Neural Networks (CNNs) achieve strong denoising performance by exploiting spatial context from neighboring pixels.

By Gihyun Kim, Jong-Seok Lee

benchmarks

arXiv Computer Vision

Aug 25

CiUNet: A Hybrid Swin-CNN UNet for Medical Image Segmentation

arXiv:2608.22281v1 Announce Type: cross Abstract: Medical image segmentation requires high accuracy and robustness, yet practical commercial deployment also demands privacy preservation and computati...

By Bin Dong, Jinghong Chen

llms computer-vision benchmarks safety

arXiv Machine Learning

Jun 4

Efficient and Training-Free Single-Image Diffusion Models

arXiv:2606. 04299v1 Announce Type: cross Abstract: We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image.

By Haojun Qiu, Kiriakos N. Kutulakos, David B. Lindell

diffusion benchmarks