https://github.com/Aitical/MCLIR
공식 코드Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
Papers with Code 아카이브
Dehazing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Algolzw/FoD
공식 코드https://github.com/BingyaoHuang/Neural-STE
공식 코드Modeling Deep Learning Based Privacy Attacks on Physical Mail
https://github.com/BookerDeWitt/MSBDN-DFF
공식 코드Multi-Scale Boosted Dehazing Network with Dense Feature Fusion
https://github.com/ChenyangLEI/deep-video-prior
공식 코드https://github.com/FanChiMao/CMFNet
공식 코드Compound Multi-branch Feature Fusion for Real Image Restoration
https://github.com/GlassyWu/AECR-Net
공식 코드https://github.com/JiaxiHe/Image-and-Video-Dehazing
공식 코드Fast Single Image Dehazing via Multilevel Wavelet Transform based Optimization
https://github.com/JoshuaEbenezer/cwgan
공식 코드Single Image Haze Removal Using Conditional Wasserstein Generative Adversarial Networks
https://github.com/MKFMIKU/PFFNet
공식 코드Progressive Feature Fusion Network for Realistic Image Dehazing
https://github.com/Owen718/ERA-Net
공식 코드Efficient Re-parameterization Residual Attention Network For Nonhomogeneous Image Dehazing
https://github.com/Owen718/Perceiving-and-Modeling-Density-is-All-You-Need-for-Image-Dehazing
공식 코드Perceiving and Modeling Density is All You Need for Image Dehazing
https://github.com/RQ-Wu/RIDCP_dehazing
공식 코드RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors
https://github.com/Seanforfun/Deep-Learning
공식 코드Generic Model-Agnostic Convolutional Neural Network for Single Image Dehazing
https://github.com/Seanforfun/GMAN_Net_Haze_Removal
공식 코드Generic Model-Agnostic Convolutional Neural Network for Single Image Dehazing
https://github.com/Troivyn/HazeCLIP
공식 코드https://github.com/XLearning-SCU/2021-IJCV-YOLY
공식 코드You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network
https://github.com/XLearning-SCU/2025-CVPR-MaIR
공식 코드MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration
https://github.com/YesianRohn/CL2S
공식 코드Rethinking the Elementary Function Fusion for Single-Image Dehazing
https://github.com/ZHKKKe/NeuralPreset
공식 코드https://github.com/ZhendongWang6/Uformer
공식 코드Uformer: A General U-Shaped Transformer for Image Restoration
https://github.com/algolzw/daclip-uir
공식 코드Controlling Vision-Language Models for Multi-Task Image Restoration
https://github.com/algolzw/image-restoration-sde
공식 코드Image Restoration with Mean-Reverting Stochastic Differential Equations
https://github.com/ameryxiong/mixdehazenet
공식 코드MixDehazeNet : Mix Structure Block For Image Dehazing Network
https://github.com/anoynymreview/underwater_simulation
공식 코드Physics Informed and Data Driven Simulation of Underwater Images via Residual Learning
https://github.com/aupendu/iterative-dehaze
공식 코드Progressive Update Guided Interdependent Networks for Single Image Dehazing
https://github.com/awesomehwang/wavedh
공식 코드WaveDH: Wavelet Sub-bands Guided ConvNet for Efficient Image Dehazing
https://github.com/ayu-22/BPPNet-Back-Projected-Pyramid-Network
공식 코드Single image dehazing for a variety of haze scenarios using back projected pyramid network
https://github.com/cddlyf/GCANet
공식 코드Gated Context Aggregation Network for Image Dehazing and Deraining
https://github.com/cecret3350/DEA-Net
공식 코드DEA-Net: Single image dehazing based on detail-enhanced convolution and content-guided attention
https://github.com/cecret3350/PTTD-Dehazing
공식 코드Prompt-based test-time real image dehazing: a novel pipeline
https://github.com/chaimi2013/FAMED-Net
공식 코드FAMED-Net: A Fast and Accurate Multi-scale End-to-end Dehazing Network
https://github.com/cnyvfang/corun-colabator
공식 코드Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
https://github.com/danaberman/underwater-hl
공식 코드Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset
https://github.com/dauing/casdyf-net
공식 코드https://github.com/dectrfov/Y-net
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.