mlsanityData to 7 Oct 2026

PeCA: Palette Context Assisted Inference for Test-Time Paint-Bucket Colourisation on Animation Videos

arXiv 2608.00903 ↗First posted 2 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In animation production, paint-bucket colourisation for hand-drawn animation is a labour-intensive procedure that assigns each enclosed region in line sketches a colour from reference design sheets. Recent automatic paint-bucket colourisation pipelines mirror this workflow via region correspondence, but correspondences can be brittle when regions are ambiguous fragments without proper context. In this paper, we propose Palette Context Assisted (PeCA), a new training-free, plug-and-play framework for animation video colourisation that aims to close this gap at test-time via reasoning over spatial and temporal contexts. Extensive experiments on existing benchmarks and a newly introduced long-video test case show consistent performance boosts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 66 references that are in the map. First posted on arXiv 2 Aug 2026.

Builds on

43 of 66 references.

References · 43

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2023Segment Anythingcited by 8,158
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2022Scalable Diffusion Models with Transformerscited by 5,931
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  8. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  9. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  10. 2025SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Featurescited by 1,127
  11. 2023CoTracker: It is Better to Track Togethercited by 516
  12. 2023Emergent Correspondence from Image Diffusioncited by 437
31 more
  1. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  2. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Modelscited by 379
  3. 2019Learning Correspondence from the Cycle-Consistency of Timecited by 269
  4. 2023MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learningcited by 171
  5. 2020Better Aggregation in Test-Time Augmentationcited by 121
  6. 2024ToonCrafter: Generative Cartoon Interpolationcited by 68
  7. 2020Deep Learning for Free-Hand Sketch: A Surveycited by 59
  8. 2024CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalizationcited by 28
  9. 2024LVCD: Reference-based Lineart Video Colorization with Diffusion Modelscited by 27
  10. 2025V-Thinker: Interactive Thinking with Imagescited by 26
  11. 2024AniDoc: Animation Creation Made Easiercited by 22
  12. 2021The Animation Transformer: Visual Correspondence via Segment Matchingcited by 20
  13. 2024Region-Based Representations Revisitedcited by 18
  14. 2024Sakuga-42M Dataset: Scaling Up Cartoon Researchcited by 17
  15. 2025Generative AI for Cel-Animation: A Surveycited by 17
  16. 2025MangaNinja: Line Art Colorization with Precise Reference Followingcited by 17
  17. 2024Learning Inclusion Matching for Animation Paint Bucket Colorizationcited by 14
  18. 2025LayerAnimate: Layer-level Control for Animationcited by 12
  19. 2025Follow-Your-Color: Multi-Instance Sketch Colorizationcited by 10
  20. 2025ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframingcited by 8
  21. 2024ColorFlow: Retrieval-Augmented Image Sequence Colorizationcited by 6
  22. 2025Cobra: Efficient Line Art COlorization with BRoAder Referencescited by 6
  23. 2025AnimeColor: Reference-based Animation Colorization with Diffusion Transformerscited by 5
  24. 2024Paint Bucket Colorization Using Anime Character Color Design Sheetscited by 3
  25. 2018Efficient semantic image segmentation with superpixel poolingcited by 2
  26. 2024Generative AI for 2D Character Animationcited by 2
  27. 2025DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Imagescited by 2
  28. 2023Improving Video Colorization by Test-Time Tuningcited by 1
  29. 2026TimeColor: Flexible Reference Colorization via Temporal Concatenationcited by 1
  30. 2026OmniColor: A Unified Framework for Multi-modal Lineart Colorizationcited by 1
  31. 2026From Pixels to Personas: Tracking the Evolution of Anime Characterscited by 1

Built on by

Not cited yet.