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.
MatchDiffusion: Training-free Generation of Match-cuts
Unpacking the Individual Components of Diffusion Policy
Steering Rectified Flow Models in the Vector Field for Controlled Image Generation
Limit Order Book Event Stream Prediction with Diffusion Model
Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts
PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution
Reward Incremental Learning in Text-to-Image Generation
Can LLMs be Good Graph Judge for Knowledge Graph Construction?
SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates
Mixed-State Quantum Denoising Diffusion Probabilistic Model
Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
StableAnimator: High-Quality Identity-Preserving Human Image Animation
Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
DiffDesign: Controllable Diffusion with Meta Prior for Efficient Interior Design Generation
An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
Comparison of Generative Learning Methods for Turbulence Modeling
Revisiting DDIM Inversion for Controlling Defect Generation by Disentangling the Background
MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing
NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model
Controllable Human Image Generation with Personalized Multi-Garments
Discrete to Continuous: Generating Smooth Transition Poses from Sign Language Observation
MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
Unlocking the Potential of Text-to-Image Diffusion with PAC-Bayesian Theory
Making Images from Images: Interleaving Denoising and Transformation
PriorDiffusion: Leverage Language Prior in Diffusion Models for Monocular Depth Estimation
Haar-Laplacian for directed graphs
$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models
Classifier-Free Guidance inside the Attraction Basin May Cause Memorization
FollowGen: A Scaled Noise Conditional Diffusion Model for Car-Following Trajectory Prediction
High-Resolution Image Synthesis via Next-Token Prediction
Prioritize Denoising Steps on Diffusion Model Preference Alignment via Explicit Denoised Distribution Estimation
DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
J-Invariant Volume Shuffle for Self-Supervised Cryo-Electron Tomogram Denoising on Single Noisy Volume
Foundation Cures Personalization: Recovering Facial Personalized Models' Prompt Consistency
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.