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.
Interpreting and Improving Diffusion Models from an Optimization Perspective
Complexity-aware Large Scale Origin-Destination Network Generation via Diffusion Model
Convolutional Recurrent Neural Network with Attention for 3D Speech Enhancement
Multi-Architecture Multi-Expert Diffusion Models
Normalization-Equivariant Neural Networks with Application to Image Denoising
Non-autoregressive Conditional Diffusion Models for Time Series Prediction
SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions
HQ-50K: A Large-scale, High-quality Dataset for Image Restoration
ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping
Joint Channel Estimation and Feedback with Masked Token Transformers in Massive MIMO Systems
Protein Discovery with Discrete Walk-Jump Sampling
PANE-GNN: Unifying Positive and Negative Edges in Graph Neural Networks for Recommendation
Phoenix: A Federated Generative Diffusion Model
Rethinking Weak Supervision in Helping Contrastive Learning
DEMIST: A deep-learning-based task-specific denoising approach for myocardial perfusion SPECT
Synthesizing realistic sand assemblies with denoising diffusion in latent space
Learning with Noisy Labels by Adaptive Gradient-Based Outlier Removal
RefineVIS: Video Instance Segmentation with Temporal Attention Refinement
DEK-Forecaster: A Novel Deep Learning Model Integrated with EMD-KNN for Traffic Prediction
GCD-DDPM: A Generative Change Detection Model Based on Difference-Feature Guided DDPM
DFormer: Diffusion-guided Transformer for Universal Image Segmentation
Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model
Enhancing Point Annotations with Superpixel and Confidence Learning Guided for Improving Semi-Supervised OCT Fluid Segmentation
Transformer-Based UNet with Multi-Headed Cross-Attention Skip Connections to Eliminate Artifacts in Scanned Documents
Microscopy image reconstruction with physics-informed denoising diffusion probabilistic model
On the Behavior of Intrusive and Non-intrusive Speech Enhancement Metrics in Predictive and Generative Settings
Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
Compressed Sensing: A Discrete Optimization Approach
Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint
Bilevel Fast Scene Adaptation for Low-Light Image Enhancement
Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping
Denoising Diffusion Semantic Segmentation with Mask Prior Modeling
DiffECG: A Versatile Probabilistic Diffusion Model for ECG Signals Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.