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/mdi-tokyotech/spatio-spectral-structure-tensor-total-variation-for-hyperspectral-image-denoising-and-destriping
공식 코드Spatio-Spectral Structure Tensor Total Variation for Hyperspectral Image Denoising and Destriping
https://github.com/mdswyz/reatco
공식 코드https://github.com/me-ditto/physics-guided-mocap
공식 코드Physics-Guided Human Motion Capture with Pose Probability Modeling
https://github.com/meclabtuda/catasynth
공식 코드Synthesising Rare Cataract Surgery Samples with Guided Diffusion Models
https://github.com/mediabrain-sjtu/led
공식 코드Leapfrog Diffusion Model for Stochastic Trajectory Prediction
https://github.com/medimair/brain-mri-processing-pipeline
공식 코드Negligible effect of brain MRI data preprocessing for tumor segmentation
https://github.com/megvii-model/HINet
공식 코드HINet: Half Instance Normalization Network for Image Restoration
https://github.com/megvii-research/NAFNet
공식 코드https://github.com/megvii-research/NBNet
공식 코드NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
https://github.com/megvii-research/PMRID
공식 코드https://github.com/megvii-research/TLC
공식 코드Improving Image Restoration by Revisiting Global Information Aggregation
https://github.com/megvii-research/far3d
공식 코드Far3D: Expanding the Horizon for Surround-view 3D Object Detection
https://github.com/megvii-research/pmn
공식 코드Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling
https://github.com/mehdi-mbl/WordCoding
공식 코드https://github.com/mehedihasanbijoy/DPCSpell
공식 코드https://github.com/mehryaragha/NoseBiometrics
공식 코드Nasal Patches and Curves for Expression-robust 3D Face Recognition
https://github.com/meijitian/zs-denoisier-hrem
공식 코드Zero-Shot Image Denoising for High-Resolution Electron Microscopy
https://github.com/melhousni/DSMNet
공식 코드Aerial Height Prediction and Refinement Neural Networks with Semantic and Geometric Guidance
https://github.com/melmaphother/timedart
공식 코드Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting
https://github.com/mengxiangming/dmps
공식 코드Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems
https://github.com/mengyuwang826/segrefiner
공식 코드SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
https://github.com/mengziyi64/cassi-self-supervised
공식 코드Self-supervised Neural Networks for Spectral Snapshot Compressive Imaging
https://github.com/meowuu7/geneoh-diffusion
공식 코드GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
https://github.com/merenguelkl/ddt
공식 코드https://github.com/merlresearch/TI2V-Zero
공식 코드TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models
https://github.com/meta-diffub/meta-diffub
공식 코드Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration
https://github.com/meteahishali/r2c-gan
공식 코드https://github.com/mi3labucm/coooler
공식 코드https://github.com/micheledelliveneri/almasim
공식 코드3D Detection and Characterisation of ALMA Sources through Deep Learning
https://github.com/micheledelliveneri/deepfocus
공식 코드3D Detection and Characterisation of ALMA Sources through Deep Learning
https://github.com/microlisk/blockchain_transaction_fee_forecasting
공식 코드Blockchain Transaction Fee Forecasting: A Comparison of Machine Learning Methods
https://github.com/microsoft/DNS-Challenge
공식 코드https://github.com/microsoft/NeuralSpeech
공식 코드PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
https://github.com/microsoft/ProphetNet
공식 코드https://github.com/microsoft/dialoglm
공식 코드DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.