DreamColour: Controllable Video Colour Editing without Training

TL;DR

DreamColour introduces a training-free, intuitive video colour editing framework that enables precise, temporally consistent colour adjustments without complex manual effort or specialized hardware.

Contribution

It proposes a novel, training-free approach that decouples spatial and temporal colour editing, combining user-friendly interfaces with advanced propagation and blending techniques.

Findings

Matches or exceeds state-of-the-art quality

Eliminates the need for training or specialized hardware

Provides an accessible, professional-quality editing tool

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.