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.
AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement
TensorLLM: Tensorising Multi-Head Attention for Enhanced Reasoning and Compression in LLMs
VideoPure: Diffusion-based Adversarial Purification for Video Recognition
Snapshot Compressed Imaging Based Single-Measurement Computer Vision for Videos
MAP-based Problem-Agnostic diffusion model for Inverse Problems
VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking
Enhanced Confocal Laser Scanning Microscopy with Adaptive Physics Informed Deep Autoencoders
On the locality bias and results in the Long Range Arena
Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation
Radio Map Estimation via Latent Domain Plug-and-Play Denoising
Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement
An Efficient Diffusion-based Non-Autoregressive Solver for Traveling Salesman Problem
Unveiling the Power of Noise Priors: Enhancing Diffusion Models for Mobile Traffic Prediction
Binary Diffusion Probabilistic Model
EFiGP: Eigen-Fourier Physics-Informed Gaussian Process for Inference of Dynamic Systems
TeD-Loc: Text Distillation for Weakly Supervised Object Localization
Sequential Change Point Detection via Denoising Score Matching
FDG-Diff: Frequency-Domain-Guided Diffusion Framework for Compressed Hazy Image Restoration
Robust Representation Consistency Model via Contrastive Denoising
Accelerate High-Quality Diffusion Models with Inner Loop Feedback
Graph Representation Learning with Diffusion Generative Models
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions
Unified 3D MRI Representations via Sequence-Invariant Contrastive Learning
Teacher Encoder-Student Decoder Denoising Guided Segmentation Network for Anomaly Detection
VipDiff: Towards Coherent and Diverse Video Inpainting via Training-free Denoising Diffusion Models
Federated Discrete Denoising Diffusion Model for Molecular Generation with OpenFL
Interaction Dataset of Autonomous Vehicles with Traffic Lights and Signs
Controlling Ensemble Variance in Diffusion Models: An Application for Reanalyses Downscaling
CNN-based TEM image denoising from first principles
Nested Annealed Training Scheme for Generative Adversarial Networks
DenoMAE: A Multimodal Autoencoder for Denoising Modulation Signals
Graph Defense Diffusion Model
Efficient Bearing Sensor Data Compression via an Asymmetrical Autoencoder with a Lifting Wavelet Transform Layer
Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction
SCDM: Score-Based Channel Denoising Model for Digital Semantic Communications
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.