https://github.com/Xiaoming-Yu/DMIT
공식 코드Multi-mapping Image-to-Image Translation via Learning Disentanglement
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Multi-mapping Image-to-Image Translation via Learning Disentanglement
Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation
Unpaired Image-to-Image Translation via Latent Energy Transport
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation
BlenDA: Domain Adaptive Object Detection through diffusion-based blending
Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation
A Time-Frequency Generative Adversarial based method for Audio Packet Loss Concealment
Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation
GANimation: Anatomically-aware Facial Animation from a Single Image
Reusing Discriminators for Encoding: Towards Unsupervised Image-to-Image Translation
Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
Two-dimensional total absorption spectroscopy with conditional generative adversarial networks
CycleGANAS: Differentiable Neural Architecture Search for CycleGAN
STEREOFOG -- Computational DeFogging via Image-to-Image Translation on a real-world Dataset
Gaze Preserving CycleGANs for Eyeglass Removal & Persistent Gaze Estimation
Physics-informed Guided Disentanglement in Generative Networks
Lightweight Modules for Efficient Deep Learning based Image Restoration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.