Cloud Emoji Dream Colour :

Controllable Video Colour Editing without Training

*Interned with SketchX
SketchX, CVSSP, University of Surrey
Demo Image.

DreamColour    introduces an intuitive, training-free framework for precise, professional-quality video colour editing, combining a user-friendly interface to deliver seamless results.

Abstract

Video colour editing is a crucial task for content creation, yet existing solutions either require painstaking frame-by-frame manipulation or produce unrealistic results with temporal artefacts. We present a practical, training-free framework that makes precise video colour editing accessible through an intuitive interface while maintaining professional-quality output. Our key insight is that by decoupling spatial and temporal aspects of colour editing, we can better align with users' natural workflow -- allowing them to focus on precise colour selection in key frames before automatically propagating changes across time.

We achieve this through a novel technical framework that combines: (i) a simple point-and-click interface merging grid-based colour selection with automatic instance segmentation for precise spatial control, (ii) bidirectional colour propagation that leverages inherent video motion patterns, and (iii) motion-aware blending that ensures smooth transitions even with complex object movements. Through extensive evaluation on diverse scenarios, we demonstrate that our approach matches or exceeds state-of-the-art methods while eliminating the need for training or specialized hardware, making professional-quality video colour editing accessible to everyone.

Architecture

Model Image.

Intra-frame colour editing pipeline.

Model Image.

Inter-frame colour editing pipeline.

Model Image.

Multi-frame colour editing pipeline.

BibTeX

@article{utintu2024dreamcolour,
      author    = {Chaitat Utintu and Pinaki Nath Chowdhury and Aneeshan Sain and Subhadeep Koley and Ayan Kumar Bhunia and Yi-Zhe Song},
      title     = {DreamColour: Controllable Video Colour Editing without Training},
      journal   = {arXiv preprint arXiv:2412.05180},
      year      = {2024},
    }