Cobra: Efficient Line Art COlorization with BRoAder References

• URL: http://arxiv.org/abs/2504.12240v1
• Date: Wed, 16 Apr 2025 16:45:19 GMT
• Title: Cobra: Efficient Line Art COlorization with BRoAder References
• Authors: Junhao Zhuang, Lingen Li, Xuan Ju, Zhaoyang Zhang, Chun Yuan, Ying Shan,
• Abstract summary: A comic page often involves diverse characters, objects, and backgrounds, which complicates the coloring process.<n>Despite advancements in diffusion models for image generation, their application in line art colorization remains limited.<n>We introduce Cobra, an efficient and versatile method that supports color hints and utilizes over 200 reference images.
• Score: 62.452143512625724
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The comic production industry requires reference-based line art colorization with high accuracy, efficiency, contextual consistency, and flexible control. A comic page often involves diverse characters, objects, and backgrounds, which complicates the coloring process. Despite advancements in diffusion models for image generation, their application in line art colorization remains limited, facing challenges related to handling extensive reference images, time-consuming inference, and flexible control. We investigate the necessity of extensive contextual image guidance on the quality of line art colorization. To address these challenges, we introduce Cobra, an efficient and versatile method that supports color hints and utilizes over 200 reference images while maintaining low latency. Central to Cobra is a Causal Sparse DiT architecture, which leverages specially designed positional encodings, causal sparse attention, and Key-Value Cache to effectively manage long-context references and ensure color identity consistency. Results demonstrate that Cobra achieves accurate line art colorization through extensive contextual reference, significantly enhancing inference speed and interactivity, thereby meeting critical industrial demands. We release our codes and models on our project page: https://zhuang2002.github.io/Cobra/.

Related papers

• Free-Lunch Color-Texture Disentanglement for Stylized Image Generation [58.406368812760256]
  This paper introduces the first tuning-free approach to achieve free-lunch color-texture disentanglement in stylized T2I generation.<n>We develop techniques for separating and extracting Color-Texture Embeddings (CTE) from individual color and texture reference images.<n>To ensure that the color palette of the generated image aligns closely with the color reference, we apply a whitening and coloring transformation.
  arXiv  Detail & Related papers  (2025-03-18T14:10:43Z)
• MangaNinja: Line Art Colorization with Precise Reference Following [84.2001766692797]
  MangaNinjia specializes in the task of reference-guided line art colorization.<n>We incorporate two thoughtful designs to ensure precise character detail transcription.<n>A patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching.
  arXiv  Detail & Related papers  (2025-01-14T18:59:55Z)
• Paint Bucket Colorization Using Anime Character Color Design Sheets [72.66788521378864]
  We introduce inclusion matching, which allows the network to understand the relationships between segments. Our network's training pipeline significantly improves performance in both colorization and consecutive frame colorization. To support our network's training, we have developed a unique dataset named PaintBucket-Character.
  arXiv  Detail & Related papers  (2024-10-25T09:33:27Z)
• Learning Inclusion Matching for Animation Paint Bucket Colorization [76.4507878427755]
  We introduce a new learning-based inclusion matching pipeline, which directs the network to comprehend the inclusion relationships between segments. Our method features a two-stage pipeline that integrates a coarse color warping module with an inclusion matching module. To facilitate the training of our network, we also develope a unique dataset, referred to as PaintBucket-Character.
  arXiv  Detail & Related papers  (2024-03-27T08:32:48Z)
• Diffusing Colors: Image Colorization with Text Guided Diffusion [11.727899027933466]
  We present a novel image colorization framework that utilizes image diffusion techniques with granular text prompts. Our method provides a balance between automation and control, outperforming existing techniques in terms of visual quality and semantic coherence. Our approach holds potential particularly for color enhancement and historical image colorization.
  arXiv  Detail & Related papers  (2023-12-07T08:59:20Z)
• Line Art Correlation Matching Feature Transfer Network for Automatic Animation Colorization [0.0]
  We propose a correlation matching feature transfer model (called CMFT) to align the colored reference feature in a learnable way. This enables the generator to transfer the layer-wise synchronized features from the deep semantic code to the content progressively.
  arXiv  Detail & Related papers  (2020-04-14T06:50:08Z)
• Deep Line Art Video Colorization with a Few References [49.7139016311314]
  We propose a deep architecture to automatically color line art videos with the same color style as the given reference images. Our framework consists of a color transform network and a temporal constraint network. Our model can achieve even better coloring results by fine-tuning the parameters with only a small amount of samples.
  arXiv  Detail & Related papers  (2020-03-24T06:57:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.