https://github.com/booooooooooo/cri
공식 코드High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Colorization is the process of adding plausible color information to monochrome photographs or videos. Colorization is a highly undetermined problem, requiring mapping a real-valued luminance image to a three-dimensional color-valued one, that has not a unique solution.
Source: ChromaGAN: An Adversarial Approach for Picture Colorization
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets
Temporal Consistent Automatic Video Colorization via Semantic Correspondence
Unsupervised Diverse Colorization via Generative Adversarial Networks
Lasagna: Layered Score Distillation for Disentangled Object Relighting
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation
Color Mismatches in Stereoscopic Video: Real-World Dataset and Deep Correction Method
Nighttime Thermal Infrared Image Colorization with Feedback-based Object Appearance Learning
Memory-Guided Collaborative Attention for Nighttime Thermal Infrared Image Colorization
SSIMBaD: Sigma Scaling with SSIM-Guided Balanced Diffusion for AnimeFace Colorization
Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
Improving Diffusion Models for Inverse Problems using Manifold Constraints
Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters
Nanoscale Microscopy Images Colorization Using Neural Networks
Generative Flows as a General Purpose Solution for Inverse Problems
Real-Time User-Guided Image Colorization with Learned Deep Priors
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
Eliminating Gradient Conflict in Reference-based Line-Art Colorization
MEM: Multi-Modal Elevation Mapping for Robotics and Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.