paper-with-me

Papers

Generative Probabilistic Image Colorization

2021-09-29 · Chie Furusawa, Shinya Kitaoka, Michael Li, Yuri Odagiri

We propose Generative Probabilistic Image Colorization, a diffusion-based generative process that trains a sequence of probabilistic models to reverse each step of noise corruption. Given a line-drawing image as input, our method suggests multiple candidate colorized images. Therefore, our method accounts for the ill-posed nature of the colorization problem. We conducted comprehensive experiments investigating the colorization of line-drawing images, report the influence of a score-based MCMC approach that corrects the marginal distribution of estimated samples, and further compare different combinations of models and the similarity of their generated images. Despite using only a relatively small training dataset, we experimentally develop a method to generate multiple diverse colorization candidates which avoids mode collapse and does not require any additional constraints, losses, or re-training with alternative training conditions. Our proposed approach performed well not only on color-conditional image generation tasks using biased initial values, but also on some practical image completion and inpainting tasks.

📄 PDF Abstract BibTeX arXiv:2109.14518

Code (0)

등록된 구현이 없습니다.

Tasks

ColorizationConditional Image GenerationImage ColorizationImage Generation

Methods 이 논문이 사용한 방법론

Colorization Colorization is a self-supervision approach that relies on colorization as the pretext task in order to learn image representations.
Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

PalGAN: Image Colorization with Palette Generative Adversarial Networks

2022-10-20 · Yi Wang, Menghan Xia, Lu Qi, Jing Shao 외

Multimodal ambiguity and color bleeding remain challenging in colorization. To tackle these problems, we propose a new GAN-based colorization approach PalGAN, integrated with palette estimation and chromatic attention. T…

ColorizationImage Colorization

Probabilistic Image Colorization

2017-05-11 · Amelie Royer, Alexander Kolesnikov, Christoph H. Lampert

We develop a probabilistic technique for colorizing grayscale natural images. In light of the intrinsic uncertainty of this task, the proposed probabilistic framework has numerous desirable properties. In particular, our…

ColorizationImage Colorization

BigColor: Colorization using a Generative Color Prior for Natural Images

2022-07-20 · Geonung Kim, Kyoungkook Kang, Seongtae Kim, Hwayoon Lee 외

For realistic and vivid colorization, generative priors have recently been exploited. However, such generative priors often fail for in-the-wild complex images due to their limited representation space. In this paper, we…

Colorization

Towards Vivid and Diverse Image Colorization with Generative Color Prior

2021-08-19 · ICCV 2021 10 · Yanze Wu, Xintao Wang, Yu Li, Honglun Zhang 외

Colorization has attracted increasing interest in recent years. Classic reference-based methods usually rely on external color images for plausible results. A large image database or online search engine is inevitably re…

ColorizationImage Colorization

Diffusing Colors: Image Colorization with Text Guided Diffusion

2023-12-07 · Nir Zabari, Aharon Azulay, Alexey Gorkor, Tavi Halperin 외

The colorization of grayscale images is a complex and subjective task with significant challenges. Despite recent progress in employing large-scale datasets with deep neural networks, difficulties with controllability an…

ColorizationImage Colorization