Language-Guided Colorization: Reconvolution and Cross-Modal Align

Previous language-guided colorization methods have obvious flaws, like color spillover and inconsistent themes. The root lies in poor info transfer and feature processing in models. Redundant data in transfer lowers efficiency and accuracy of feature representation. Existing feature-fusion modules also can’t integrate diverse features well, harming colorization. We propose a new approach with two key modules. The Reconstruction Convolution Module (RCM) cuts costs by removing redundant info and strengthens feature representation. The Cross-Modal Color Aligner Module (CMCAM) uses multi-scale features to align color and grayscale features precisely, improving semantic understanding. Experiments show our method outperforms state-of-the-art, achieving better results and robustness in high-quality color image generation.

• Publication year

  2025

• Venue

  2025 IEEE/CIC International Conference on Communications in China (ICCC)

• Publication date

  2025-08-10

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICCC65529.2025.11149340
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Control Color: Multimodal Diffusion-Based Interactive Image Colorization

  2024cited by this paper
• L-CoIns: Language-based Colorization With Instance Awareness

  2023cited by this paper
• StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing

  2023cited by this paper
• Localizing Object-level Shape Variations with Text-to-Image Diffusion Models

  2023cited by this paper
• Adding Conditional Control to Text-to-Image Diffusion Models

  2023cited by this paper
• Zero-shot Image-to-Image Translation

  2023cited by this paper
• Supplementary Materials for: NULL-text Inversion for Editing Real Images using Guided Diffusion Models

  2023cited by this paper
• L-CoDer: Language-Based Colorization with Color-Object Decoupling Transformer

  2022influential reference
• Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

  2022cited by this paper
• Classifier-Free Diffusion Guidance

  2022cited by this paper
• L-CoDe: Language-Based Colorization Using Color-Object Decoupled Conditions

  2022influential reference
• BigColor: Colorization using a Generative Color Prior for Natural Images

  2022cited by this paper
• Prompt-to-Prompt Image Editing with Cross Attention Control

  2022cited by this paper
• UniColor

  2022cited by this paper
• DiffEdit: Diffusion-based semantic image editing with mask guidance

  2022cited by this paper
• InstructPix2Pix: Learning to Follow Image Editing Instructions

  2022cited by this paper
• Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation

  2022cited by this paper
• SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations

  2021cited by this paper
• Learning Transferable Visual Models From Natural Language Supervision

  2021cited by this paper
• Colorization Transformer

  2021cited by this paper
• ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models

  2021cited by this paper
• Towards Vivid and Diverse Image Colorization with Generative Color Prior

  2021cited by this paper
• Mask Transfiner for High-Quality Instance Segmentation

  2021cited by this paper
• High-Resolution Image Synthesis with Latent Diffusion Models

  2021influential reference
• Instance-Aware Image Colorization

  2020cited by this paper
• Language-Guided Image Colorization

  2018cited by this paper
• Learning to Color from Language

  2018cited by this paper
• Pixel-level Semantics Guided Image Colorization

  2018cited by this paper
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

  2017cited by this paper
• Language-Based Image Editing with Recurrent Attentive Models

  2017cited by this paper
• Rethinking Atrous Convolution for Semantic Image Segmentation

  2017cited by this paper
• Learning Representations for Automatic Colorization

  2016cited by this paper
• Learning Diverse Image Colorization

  2016cited by this paper
• Deep Colorization

  2015cited by this paper
• Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position

  1980cited by this paper
• Supplmentary Material: L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors

  year unknowninfluential reference

• No citing papers are available for this paper.