OmniColor: A Unified Framework for Multi-modal Lineart Colorization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Xulu, Du, Haoqian, Wei, Xiaoyong, Li, Qing
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914429878140928
author Zhang, Xulu
Du, Haoqian
Wei, Xiaoyong
Li, Qing
author_facet Zhang, Xulu
Du, Haoqian
Wei, Xiaoyong
Li, Qing
contents Lineart colorization is a critical stage in professional content creation, yet achieving precise and flexible results under diverse user constraints remains a significant challenge. To address this, we propose OmniColor, a unified framework for multi-modal lineart colorization that supports arbitrary combinations of control signals. Specifically, we systematically categorize guidance signals into two types: spatially-aligned conditions and semantic-reference conditions. For spatially-aligned inputs, we employ a dual-path encoding strategy paired with a Dense Feature Alignment loss to ensure rigorous boundary preservation and precise color restoration. For semantic-reference inputs, we utilize a VLM-only encoding scheme integrated with a Temporal Redundancy Elimination mechanism to filter repetitive information and enhance inference efficiency. To resolve potential input conflicts, we introduce an Adaptive Spatial-Semantic Gating module that dynamically balances multi-modal constraints. Experimental results demonstrate that OmniColor achieves superior controllability, visual quality, and temporal stability, providing a robust and practical solution for lineart colorization. The source code and dataset will be open at https://github.com/zhangxulu1996/OmniColor.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27531
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OmniColor: A Unified Framework for Multi-modal Lineart Colorization
Zhang, Xulu
Du, Haoqian
Wei, Xiaoyong
Li, Qing
Computer Vision and Pattern Recognition
Lineart colorization is a critical stage in professional content creation, yet achieving precise and flexible results under diverse user constraints remains a significant challenge. To address this, we propose OmniColor, a unified framework for multi-modal lineart colorization that supports arbitrary combinations of control signals. Specifically, we systematically categorize guidance signals into two types: spatially-aligned conditions and semantic-reference conditions. For spatially-aligned inputs, we employ a dual-path encoding strategy paired with a Dense Feature Alignment loss to ensure rigorous boundary preservation and precise color restoration. For semantic-reference inputs, we utilize a VLM-only encoding scheme integrated with a Temporal Redundancy Elimination mechanism to filter repetitive information and enhance inference efficiency. To resolve potential input conflicts, we introduce an Adaptive Spatial-Semantic Gating module that dynamically balances multi-modal constraints. Experimental results demonstrate that OmniColor achieves superior controllability, visual quality, and temporal stability, providing a robust and practical solution for lineart colorization. The source code and dataset will be open at https://github.com/zhangxulu1996/OmniColor.
title OmniColor: A Unified Framework for Multi-modal Lineart Colorization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.27531