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/yangchen1997/wcdt
공식 코드WcDT: World-centric Diffusion Transformer for Traffic Scene Generation
https://github.com/yanggaouq/ssdm-mri
공식 코드Highly Undersampled MRI Reconstruction via a Single Posterior Sampling of Diffusion Models
https://github.com/yangling0818/realcompo
공식 코드RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
https://github.com/yangling0818/videotetris
공식 코드https://github.com/yangqy1110/nc-sdedit
공식 코드https://github.com/yangzhaojason/DualDiff
공식 코드DualDiff+: Dual-Branch Diffusion for High-Fidelity Video Generation with Reward Guidance
https://github.com/yangzhengyi98/dreamrec
공식 코드Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion
https://github.com/yanliang3612/nucleusdiff
공식 코드Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design
https://github.com/yanweiyue/FastGLT
공식 코드Fast Track to Winning Tickets: Repowering One-Shot Pruning for Graph Neural Networks
https://github.com/yanzipei/vf_red
공식 코드Generalized Robust Fundus Photography-based Vision Loss Estimation for High Myopia
https://github.com/yaojieliu/ECCV2018-FaceDeSpoofing
공식 코드https://github.com/yasahi-hpc/generative-enkf
공식 코드https://github.com/yasumasaonoe/DenoiseET
공식 코드Learning to Denoise Distantly-Labeled Data for Entity Typing
https://github.com/yazidjanati/cfgig
공식 코드Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance
https://github.com/yazidjanati/mgps
공식 코드Variational Diffusion Posterior Sampling with Midpoint Guidance
https://github.com/yaziwel/all-in-one-medical-image-restoration-via-task-adaptive-routing
공식 코드All-In-One Medical Image Restoration via Task-Adaptive Routing
https://github.com/yaziwel/feat
공식 코드FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation
https://github.com/yaziwel/region-attention-transformer-for-medical-image-restoration
공식 코드https://github.com/yaziwel/restore-rwkv
공식 코드Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV
https://github.com/ybu-lxd/SRNDiff
공식 코드SRNDiff: Short-term Rainfall Nowcasting with Condition Diffusion Model
https://github.com/ybzh/point-dae
공식 코드Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning
https://github.com/yc015/scene-representation-diffusion-model
공식 코드Beyond Surface Statistics: Scene Representations in a Latent Diffusion Model
https://github.com/ychfan/nsr
공식 코드https://github.com/ychfan/scn
공식 코드https://github.com/ycl92/tmd-ldct
공식 코드Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography
https://github.com/yeates/promptfix
공식 코드https://github.com/yec22/fine-grained-indoor-recon
공식 코드https://github.com/yeeesir/dvs_rdnet
공식 코드Restoring Real-World Degraded Events Improves Deblurring Quality
https://github.com/yepengliu/ctrlregen
공식 코드Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
https://github.com/yeungchenwa/fontdiffuser
공식 코드https://github.com/yftah89/Neural-SCL-Domain-Adaptation
공식 코드Neural Structural Correspondence Learning for Domain Adaptation
https://github.com/yftah89/Neural-SCLDomain-Adaptation
공식 코드Neural Structural Correspondence Learning for Domain Adaptation
https://github.com/yhZhai/idol
공식 코드IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation
https://github.com/yhli123/immiscible-diffusion
공식 코드Improved Immiscible Diffusion: Accelerate Diffusion Training by Reducing Its Miscibility
https://github.com/yichen928/x-drive
공식 코드X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.