Papers with Code 아카이브
Denoising
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 6
- 보존된 평가 기록
- 15
Denoising is a task in image processing and computer vision that aims to remove or reduce noise from an image. Noise can be introduced into an image due to various reasons, such as camera sensor limitations, lighting conditions, and compression artifacts. The goal of denoising is to recover the original image, which is considered to be noise-free, from a noisy observation.
<span style="color:grey; opacity: 0.6">( Image credit: Beyond a Gaussian Denoiser )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/czg1225/asyncdiff
공식 코드AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
https://github.com/da03/markup2im
공식 코드https://github.com/daheekwon/c3
공식 코드Enhancing Creative Generation on Stable Diffusion-based Models
https://github.com/daidaijr/eamamba
공식 코드EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
https://github.com/danedane-haider/Almost-Smooth-Sailing
공식 코드https://github.com/daniela997/filmdamagesimulator
공식 코드Simulating analogue film damage to analyse and improve artefact restoration on high-resolution scans
https://github.com/danielement321/fm2s
공식 코드https://github.com/daniil-selikhanovych/asbm
공식 코드https://github.com/dannie125/mm-bsn
공식 코드MM-BSN: Self-Supervised Image Denoising for Real-World with Multi-Mask based on Blind-Spot Network
https://github.com/dannis97500/pm-moe
공식 코드PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning
https://github.com/daqians/charformer
공식 코드CharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising
https://github.com/dariant/id-booth
공식 코드ID-Booth: Identity-consistent Face Generation with Diffusion Models
https://github.com/darioShar/DLPM
공식 코드https://github.com/darshangm/diffusion-nonlinear-control
공식 코드https://github.com/dasongli1/learning_degradation
공식 코드https://github.com/dasongli1/shift-net
공식 코드A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
https://github.com/david-stojanovski/EDMLX
공식 코드Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms
https://github.com/david-stojanovski/echo_from_noise
공식 코드https://github.com/daviddmc/Deform2Self
공식 코드Deformed2Self: Self-Supervised Denoising for Dynamic Medical Imaging
https://github.com/davidhalladay/frido
공식 코드Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis
https://github.com/davismeee/lightdiff
공식 코드LighTDiff: Surgical Endoscopic Image Low-Light Enhancement with T-Diffusion
https://github.com/dawn-lx/causalcache-vdm
공식 코드Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
https://github.com/dbstjswo505/FRAG
공식 코드https://github.com/ddgoodgood/trce
공식 코드TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
https://github.com/ddlee-cn/mulut
공식 코드Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables
https://github.com/ddsediri/iterativepfn
공식 코드https://github.com/deadsmither5/DogLayout
공식 코드DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generation
https://github.com/debadityaqu/rddm
공식 코드Region-Disentangled Diffusion Model for High-Fidelity PPG-to-ECG Translation
https://github.com/decisionintelligence/adformer
공식 코드ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting
https://github.com/declare-lab/mm-align
공식 코드https://github.com/deegy666/add-rsc
공식 코드Adaptive Differential Denoising for Respiratory Sounds Classification
https://github.com/deep-kaixun/videopure
공식 코드VideoPure: Diffusion-based Adversarial Purification for Video Recognition
https://github.com/deepgraphlearning/diffpack
공식 코드DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing
https://github.com/deepgraphlearning/siamdiff
공식 코드Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction
https://github.com/deeplearningps/ecconf
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.