TimeColor: Flexible Reference Colorization via Temporal Concatenation

• URL: http://arxiv.org/abs/2601.00296v1
• Date: Thu, 01 Jan 2026 10:30:38 GMT
• Title: TimeColor: Flexible Reference Colorization via Temporal Concatenation
• Authors: Bryan Constantine Sadihin, Yihao Meng, Michael Hua Wang, Matteo Jiahao Chen, Hang Su,
• Abstract summary: TimeColor is a sketch-based video colorization model that supports variable-count references with explicit per-reference assignment.<n>TimeColor encodes latent frames which are diffusiond temporally, permitting them to be processed concurrently in each step.<n> Experiments show that TimeColor improves color fidelity, identity consistency, and temporal stability over prior baselines.
• Score: 12.270750223921276
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Most colorization models condition only on a single reference, typically the first frame of the scene. However, this approach ignores other sources of conditional data, such as character sheets, background images, or arbitrary colorized frames. We propose TimeColor, a sketch-based video colorization model that supports heterogeneous, variable-count references with the use of explicit per-reference region assignment. TimeColor encodes references as additional latent frames which are concatenated temporally, permitting them to be processed concurrently in each diffusion step while keeping the model's parameter count fixed. TimeColor also uses spatiotemporal correspondence-masked attention to enforce subject-reference binding in addition to modality-disjoint RoPE indexing. These mechanisms mitigate shortcutting and cross-identity palette leakage. Experiments on SAKUGA-42M under both single- and multi-reference protocols show that TimeColor improves color fidelity, identity consistency, and temporal stability over prior baselines.

Related papers

• ColorFlow: Retrieval-Augmented Image Sequence Colorization [65.93834649502898]
  We propose a three-stage diffusion-based framework tailored for image sequence colorization in industrial applications.<n>Unlike existing methods that require per-ID finetuning or explicit ID embedding extraction, we propose a novel Retrieval Augmented Colorization pipeline.<n>Our pipeline also features a dual-branch design: one branch for color identity extraction and the other for colorization.
  arXiv  Detail & Related papers  (2024-12-16T14:32:49Z)
• 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)
• L-C4: Language-Based Video Colorization for Creative and Consistent Color [59.069498113050436]
  We present Language-based video colorization for Creative and Consistent Colors (L-C4) Our model is built upon a pre-trained cross-modality generative model. We propose temporally deformable attention to prevent flickering or color shifts, and cross-clip fusion to maintain long-term color consistency.
  arXiv  Detail & Related papers  (2024-10-07T12:16:21Z)
• Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis [16.634138745034733]
  We present the first training-free, test-time-only method to disentangle and condition text-to-image models on color and style attributes from reference image.
  arXiv  Detail & Related papers  (2024-09-04T04:16:58Z)
• Control Color: Multimodal Diffusion-based Interactive Image Colorization [81.68817300796644]
  Control Color (Ctrl Color) is a multi-modal colorization method that leverages the pre-trained Stable Diffusion (SD) model. We present an effective way to encode user strokes to enable precise local color manipulation. 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.
  arXiv  Detail & Related papers  (2024-02-16T17:51:13Z)
• Temporal Consistent Automatic Video Colorization via Semantic Correspondence [12.107878178519128]
  We propose a novel video colorization framework, which combines semantic correspondence into automatic video colorization. In the NTIRE 2023 Video Colorization Challenge, our method ranks at the 3rd place in Color Distribution Consistency (CDC) Optimization track.
  arXiv  Detail & Related papers  (2023-05-13T12:06:09Z)
• BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization [70.14893481468525]
  We present an effective BiSTNet to explore colors of reference exemplars and utilize them to help video colorization. We first establish the semantic correspondence between each frame and the reference exemplars in deep feature space to explore color information from reference exemplars. We develop a mixed expert block to extract semantic information for modeling the object boundaries of frames so that the semantic image prior can better guide the colorization process.
  arXiv  Detail & Related papers  (2022-12-05T13:47:15Z)
• Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning [90.38674162878496]
  We propose a novel temporally consistent video colorization framework (TCVC) TCVC effectively propagates frame-level deep features in a bidirectional way to enhance the temporal consistency of colorization. Experiments demonstrate that our method can not only obtain visually pleasing colorized video, but also achieve clearly better temporal consistency than state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-10-09T13:00:14Z)
• Reference-Based Video Colorization with Spatiotemporal Correspondence [8.472559058510205]
  We propose a reference-based video colorization framework with temporal correspondence. By restricting temporally-related regions for referencing colors, our approach propagates faithful colors throughout the video.
  arXiv  Detail & Related papers  (2020-11-25T05:47:38Z)

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.