paper-with-me

Image Denoising

21개 벤치마크 · 논문 1,317편 · 이 태스크의 논문 보기 →

Benchmarks

SIDD

결과 66개

DND

결과 48개

ELD SonyA7S2 x200

결과 30개

SID SonyA7S2 x250

결과 30개

ELD SonyA7S2 x100

결과 27개

SID x100

결과 24개

SID x300

결과 24개

SID SonyA7S2 x100

결과 15개

Urban100 sigma50

결과 12개

urban100 sigma15

결과 12개

BSD68 sigma50

결과 6개

SID SonyA7S2 x300

결과 6개

Urban100 sigma25

결과 6개

BSD68 sigma30

결과 3개

FFHQ

결과 3개

FMD

결과 3개

Nam

결과 3개

PolyU

결과 3개

Most implemented

Learning to See in the Dark

2018-05-04 · 구현 19개

Deep Image Prior

2017-11-29 · 구현 14개

Simple Baselines for Image Restoration

2022-04-10 · 구현 13개

Papers

Efficient 3D Whole-Body PET Image Denoising via Conditional Rectified Flow With Optimized Sampling Strategy

2026-09-15 · Jiale Shen, Guolin Wang, Chenhao Wang, Xinhui Su 외 arxiv

Reducing radiation exposure in Positron Emission Tomography (PET) is important for patient safety; however, ultra-low-dose imaging suffers from severe noise, which may affect diagnostic interpretation without appropriate…

Computational EfficiencyImage EnhancementImage Denoising

TT-net: Quantum Inspired Tensor Network Denoising in Conditional GANs

2026-08-20 · Michal A. Sterzel, Marko J. Rančić arxiv

Developed as a workhorse for classical simulations of quantum algorithms and quantum many-body systems, Tensor Network methods have entered the scientific mainstream in quantum physics. Among various types of tensor netw…

Image Denoising

VLM- and LLM-Driven Multi-Agent System for PET Image Denoising

2026-08-13 · Boxiao Yu, Savas Ozdemir, Yang Xing, Fumio Hashimoto 외 arxiv

Positron emission tomography (PET) imaging suffers from limited spatial resolution and low signal-to-noise ratio, which can compromise quantitative accuracy and lesion detectability. Deep learning-based denoising methods…

Image Denoising

LiteKD-Net: Lightweight Knowledge-Distilled Network for Mobile Image Denoising

2026-08-06 · Zhou Zhiyi arxiv

Mobile image denoising requires both good restoration quality and low computational cost. In addition, it's annoying to collect large-scale LQ-GT clean pairs. As a result, we propose LiteKD-Net, a lightweight knowledge-d…

Computational EfficiencyKnowledge DistillationImage Denoising

YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generation

2026-07-10 · Jaekyun Ko, Byung Wan Lim, Soomin Lee, Dongjin Kim 외 arxiv

Real-world sRGB image denoising remains challenging due to the nonlinear characteristics of sensor noise and the difficulty of acquiring aligned clean-noisy image pairs. Supervised denoisers often overfit to limited pair…

Image Denoising

Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process

2026-07-04 · Zican Hu, Xuyang Hu, Yiming Liu, Zuwei Long 외 hf

Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge. Exist…

Reinforcement LearningSpatial ReasoningImage GenerationImage Denoising

전체 1,317편 보기 →