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>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Unsupervised Microscopy Video Denoising
OneActor: Consistent Character Generation via Cluster-Conditioned Guidance
OmniSSR: Zero-shot Omnidirectional Image Super-Resolution using Stable Diffusion Model
Assessing The Impact of CNN Auto Encoder-Based Image Denoising on Image Classification Tasks
Generating Human Interaction Motions in Scenes with Text Control
Molecular relaxation by reverse diffusion with time step prediction
Masked and Shuffled Blind Spot Denoising for Real-World Images
TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation
HSIDMamba: Exploring Bidirectional State-Space Models for Hyperspectral Denoising
Digging into contrastive learning for robust depth estimation with diffusion models
RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion
NIR-Assisted Image Denoising: A Selective Fusion Approach and A Real-World Benchmark Dataset
Lossy Image Compression with Foundation Diffusion Models
Synthesis of Through-Wall Micro-Doppler Signatures of Human Motions Using Generative Adversarial Networks
Multibranch Generative Models for Multichannel Imaging with an Application to PET/CT Synergistic Reconstruction
ConsistencyDet: A Few-step Denoising Framework for Object Detection Using the Consistency Model
Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
Taming Stable Diffusion for Text to 360° Panorama Image Generation
Classifier-guided neural blind deconvolution: a physics-informed denoising module for bearing fault diagnosis under heavy noise
Efficient Denoising using Score Embedding in Score-based Diffusion Models
DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space
Adversarial purification for no-reference image-quality metrics: applicability study and new methods
Move Anything with Layered Scene Diffusion
GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models
Deep Generative Sampling in the Dual Divergence Space: A Data-efficient & Interpretative Approach for Generative AI
Single Stage Adaptive Multi-Attention Network for Image Restoration
LIPT: Latency-aware Image Processing Transformer
Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
scRDiT: Generating single-cell RNA-seq data by diffusion transformers and accelerating sampling
Quantum State Generation with Structure-Preserving Diffusion Model
High Noise Scheduling is a Must
GeoDirDock: Guiding Docking Along Geodesic Paths
Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.