Colorization
156 papers with code • 2 benchmarks • 7 datasets
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
Benchmarks
These leaderboards are used to track progress in Colorization
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Colorization models and implementations
SPair-71k
ImageNet ctest10k
SketchyScene
NCD
QST
AnimeCeleb
Latest papers with no code
Zero-shot Point Cloud Completion Via 2D Priors
3D point cloud completion is designed to recover complete shapes from partially observed point clouds.
Automatic Controllable Colorization via Imagination
Unlike most previous end-to-end automatic colorization algorithms, our framework allows for iterative and localized modifications of the colorization results because we explicitly model the coloring samples.
GenN2N: Generative NeRF2NeRF Translation
We present GenN2N, a unified NeRF-to-NeRF translation framework for various NeRF translation tasks such as text-driven NeRF editing, colorization, super-resolution, inpainting, etc.
Translation-based Video-to-Video Synthesis
Translation-based Video Synthesis (TVS) has emerged as a vital research area in computer vision, aiming to facilitate the transformation of videos between distinct domains while preserving both temporal continuity and underlying content features.
Generative Quanta Color Imaging
In this paper, we explore the possibility of generating a color image from a single binary frame of a single-photon camera.
Lift3D: Zero-Shot Lifting of Any 2D Vision Model to 3D
In recent years, there has been an explosion of 2D vision models for numerous tasks such as semantic segmentation, style transfer or scene editing, enabled by large-scale 2D image datasets.
CCC++: Optimized Color Classified Colorization with Segment Anything Model (SAM) Empowered Object Selective Color Harmonization
We compare our proposed model with state-of-the-art models using six different dataset: Place, ADE, Celeba, COCO, Oxford 102 Flower, and ImageNet, in qualitative and quantitative approaches.
CCC: Color Classified Colorization
During training, we propose a class-weighted function based on true class appearance in each batch to ensure proper color saturation of individual objects.
Colorizing Monochromatic Radiance Fields
Though Neural Radiance Fields (NeRF) can produce colorful 3D representations of the world by using a set of 2D images, such ability becomes non-existent when only monochromatic images are provided.
Control Color: Multimodal Diffusion-based Interactive Image Colorization
We also introduce a novel module based on self-attention and a content-guided deformable autoencoder to address the long-standing issues of color overflow and inaccurate coloring.
