Papers with Code 아카이브
Image Dehazing
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 15
- 보존된 평가 기록
- 117
<span style="color:grey; opacity: 0.6">( Image credit: Densely Connected Pyramid Dehazing Network )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/proteus1991/GridDehazeNet
공식 코드GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
https://github.com/redlessme/transmission-bvm
공식 코드Transmission-Guided Bayesian Generative Model for Smoke Segmentation
https://github.com/robustsam/RobustSAM
공식 코드https://github.com/ruiyi-w/learning-hazing-to-dehazing
공식 코드Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing
https://github.com/sunj000/wdmamba
공식 코드WDMamba: When Wavelet Degradation Prior Meets Vision Mamba for Image Dehazing
https://github.com/supersupercong/selfpromer
공식 코드SelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency
https://github.com/supersupercong/uhdformer
공식 코드Correlation Matching Transformation Transformers for UHD Image Restoration
https://github.com/swu-cs-medialab/lkd-net
공식 코드LKD-Net: Large Kernel Convolution Network for Single Image Dehazing
https://github.com/tanvirnwu/hazespace2m
공식 코드https://github.com/tianwenzhou/prodehaze
공식 코드ProDehaze: Prompting Diffusion Models Toward Faithful Image Dehazing
https://github.com/tranleanh/dpte-net
공식 코드Distilled Pooling Transformer Encoder for Efficient Realistic Image Dehazing
https://github.com/tranleanh/edn-gtm
공식 코드A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing
https://github.com/tranleanh/rsvt
공식 코드Haze Removal via Regional Saturation-Value Translation and Soft Segmentation
https://github.com/txphome/dfpir
공식 코드Degradation-Aware Feature Perturbation for All-in-One Image Restoration
https://github.com/vladimirescu/robustdehazing
공식 코드Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing
https://github.com/w-jilly/frequency-compensated-diffusion-model-pytorch
공식 코드Frequency Compensated Diffusion Model for Real-scene Dehazing
https://github.com/wangzrk/LMHaze
공식 코드LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset
https://github.com/wengzp1/scaleupdehazing
공식 코드https://github.com/whrws/nhrnet
공식 코드Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning
https://github.com/xiaofeng-life/awesomedehazing
공식 코드A Comprehensive Survey and Taxonomy on Single Image Dehazing Based on Deep Learning
https://github.com/xiaofeng-life/icdehazing
공식 코드Illumination Controllable Dehazing Network based on Unsupervised Retinex Embedding
https://github.com/xiaofeng-life/sfsnid
공식 코드https://github.com/yangyiliu21/ntire2023_itbdehaze
공식 코드A Data-Centric Solution to NonHomogeneous Dehazing via Vision Transformer
https://github.com/yanli-ly/dehazing-drn
공식 코드Single Image Dehazing with An Independent Detail-Recovery Network
https://github.com/yuhuustc/dehazeddpm
공식 코드https://github.com/yuzheng9/c2pnet
공식 코드Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
https://github.com/ywxjm/diff-dehazer
공식 코드Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training
https://github.com/yz-wang/togethernet
공식 코드https://github.com/yz-wang/ucl-dehaze
공식 코드UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning
https://github.com/yzxing87/pytorch-deep-video-prior
공식 코드https://github.com/zhengchuanpan/GMAN
공식 코드GMAN: A Graph Multi-Attention Network for Traffic Prediction
https://github.com/zhilin007/FFA-Net
공식 코드FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
https://github.com/zhoushen1/dcmpnet
공식 코드Depth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
https://github.com/zzhlovexuexi/tsnet
공식 코드TSNet:A Two-stage Network for Image Dehazing with Multi-scale Fusion and Adaptive Learning
https://github.com/zzr-idam/4KDehazing
공식 코드4K-HAZE: A Dehazing Benchmark with 4K Resolution Hazy and Haze-Free Images
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.