Papers with Code 아카이브
Image-to-Image Translation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 38
- 보존된 평가 기록
- 195
Image-to-Image Translation is a task in computer vision and machine learning where the goal is to learn a mapping between an input image and an output image, such that the output image can be used to perform a specific task, such as style transfer, data augmentation, or image restoration.
<span style="color:grey; opacity: 0.6">( Image credit: Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images
Mask2Lesion: Mask-Constrained Adversarial Skin Lesion Image Synthesis
What and Where to Translate: Local Mask-based Image-to-Image Translation
Artifact Disentanglement Network for Unsupervised Metal Artifact Reduction
Cross-Domain Cascaded Deep Feature Translation
Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy
ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation
Combining Noise-to-Image and Image-to-Image GANs: Brain MR Image Augmentation for Tumor Detection
Towards Photo-Realistic Visible Watermark Removal with Conditional Generative Adversarial Networks
AlignFlow: Cycle Consistent Learning from Multiple Domains via Normalizing Flows
Image-to-Image Translation with Multi-Path Consistency Regularization
Batch weight for domain adaptation with mass shift
Video-to-Video Translation for Visual Speech Synthesis
A Plug-in Method for Representation Factorization in Connectionist Models
Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation
Textured Neural Avatars
Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving
Joint haze image synthesis and dehazing with mmd-vae losses
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
One-Shot Image-to-Image Translation via Part-Global Learning with a Multi-adversarial Framework
Label-Noise Robust Multi-Domain Image-to-Image Translation
Few-Shot Unsupervised Image-to-Image Translation
Towards Instance-level Image-to-Image Translation
DRIT++: Diverse Image-to-Image Translation via Disentangled Representations
Learn to synthesize and synthesize to learn
CT-To-MR Conditional Generative Adversarial Networks for Ischemic Stroke Lesion Segmentation
Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification
Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
Face Video Generation from a Single Image and Landmarks
Bidirectional Learning for Domain Adaptation of Semantic Segmentation
Switchable Whitening for Deep Representation Learning
Automatic Temporally Coherent Video Colorization
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.