Saved in:
Bibliographic Details
Main Authors: Utintu, Chaitat, Chowdhury, Pinaki Nath, Sain, Aneeshan, Koley, Subhadeep, Bhunia, Ayan Kumar, Song, Yi-Zhe
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.05180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929618433343488
author Utintu, Chaitat
Chowdhury, Pinaki Nath
Sain, Aneeshan
Koley, Subhadeep
Bhunia, Ayan Kumar
Song, Yi-Zhe
author_facet Utintu, Chaitat
Chowdhury, Pinaki Nath
Sain, Aneeshan
Koley, Subhadeep
Bhunia, Ayan Kumar
Song, Yi-Zhe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05180
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DreamColour: Controllable Video Colour Editing without Training
Utintu, Chaitat
Chowdhury, Pinaki Nath
Sain, Aneeshan
Koley, Subhadeep
Bhunia, Ayan Kumar
Song, Yi-Zhe
Computer Vision and Pattern Recognition
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.
title DreamColour: Controllable Video Colour Editing without Training
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.05180