https://github.com/xinghaow99/denosent
공식 코드DenoSent: A Denoising Objective for Self-Supervised Sentence Representation Learning
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/xingy038/dreamer-xl
공식 코드Dreamer XL: Towards High-Resolution Text-to-3D Generation via Trajectory Score Matching
https://github.com/xiongchaochen/dudocfnet-multitask
공식 코드https://github.com/xiuheng-wang/Plug_and_Play_HSI_unmixing
공식 코드https://github.com/xiuheng-wang/tuning_free_pnp_hsi_deconvolution
공식 코드Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
https://github.com/xj-zhu98/krdn
공식 코드Knowledge-refined Denoising Network for Robust Recommendation
https://github.com/xj231/FDN
공식 코드A Fusion-Denoising Attack on InstaHide with Data Augmentation
https://github.com/xjli360/VisCtrl
공식 코드Tuning-Free Visual Customization via View Iterative Self-Attention Control
https://github.com/xkli-allen/lightdic
공식 코드LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
https://github.com/xl-tang3/RCOT
공식 코드https://github.com/xlearning-scu/2022-neurips-msanet
공식 코드https://github.com/xmed-lab/cpr
공식 코드Context-Aware Pseudo-Label Refinement for Source-Free Domain Adaptive Fundus Image Segmentation
https://github.com/xmed-lab/diffcmr
공식 코드DiffCMR: Fast Cardiac MRI Reconstruction with Diffusion Probabilistic Models
https://github.com/xmed-lab/fd-sos
공식 코드https://github.com/xmed-lab/geca
공식 코드https://github.com/xmindflow/INCODE
공식 코드INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings
https://github.com/xpixelgroup/diffbir
공식 코드DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior
https://github.com/xpixelgroup/hat
공식 코드https://github.com/xu-shitong/diffusion-image-captioning
공식 코드CLIP-Diffusion-LM: Apply Diffusion Model on Image Captioning
https://github.com/xuandongzhao/watermarkattacker
공식 코드Invisible Image Watermarks Are Provably Removable Using Generative AI
https://github.com/xuanliu2000/vgcdm
공식 코드Generating HSR Bogie Vibration Signals via Pulse Voltage-Guided Conditional Diffusion Model
https://github.com/xugao97/AttentionDistillation
공식 코드Attention Distillation: A Unified Approach to Visual Characteristics Transfer
https://github.com/xumaomao94/LaPnP
공식 코드Radio Map Estimation via Latent Domain Plug-and-Play Denoising
https://github.com/xuyanwu/SIDDMs-UFOGen
공식 코드https://github.com/xuyizdby/noiseerasar
공식 코드https://github.com/xyliu339/osdd
공식 코드https://github.com/xylonxu01/tfs-diff
공식 코드Simultaneous Tri-Modal Medical Image Fusion and Super-Resolution using Conditional Diffusion Model
https://github.com/xypeng9903/k-diffusion-inverse-problems
공식 코드Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
https://github.com/xypeng9903/ncvsd
공식 코드https://github.com/xyuan01/self-supervised-noise2noise-for-ldct
공식 코드https://github.com/xyvirtualgroup/adaptivepnp_sci
공식 코드Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging
https://github.com/xzwhan/card
공식 코드https://github.com/y-debug-sys/diffusion-ts
공식 코드Diffusion-TS: Interpretable Diffusion for General Time Series Generation
https://github.com/y-zhang-hf/NeighborhoodSmoothing
공식 코드Estimating network edge probabilities by neighborhood smoothing
https://github.com/yanbinhe/dsr
공식 코드Kronecker-structured Sparse Vector Recovery with Application to IRS-MIMO Channel Estimation
https://github.com/yandex-research/ddpm-segmentation
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.