It's All About Your Sketch: Democratising Sketch Control in Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koley, Subhadeep, Bhunia, Ayan Kumar, Sekhri, Deeptanshu, Sain, Aneeshan, Chowdhury, Pinaki Nath, Xiang, Tao, Song, Yi-Zhe
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916169446850560
author Koley, Subhadeep
Bhunia, Ayan Kumar
Sekhri, Deeptanshu
Sain, Aneeshan
Chowdhury, Pinaki Nath
Xiang, Tao
Song, Yi-Zhe
author_facet Koley, Subhadeep
Bhunia, Ayan Kumar
Sekhri, Deeptanshu
Sain, Aneeshan
Chowdhury, Pinaki Nath
Xiang, Tao
Song, Yi-Zhe
contents This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI. We importantly democratise the process, enabling amateur sketches to generate precise images, living up to the commitment of "what you sketch is what you get". A pilot study underscores the necessity, revealing that deformities in existing models stem from spatial-conditioning. To rectify this, we propose an abstraction-aware framework, utilising a sketch adapter, adaptive time-step sampling, and discriminative guidance from a pre-trained fine-grained sketch-based image retrieval model, working synergistically to reinforce fine-grained sketch-photo association. Our approach operates seamlessly during inference without the need for textual prompts; a simple, rough sketch akin to what you and I can create suffices! We welcome everyone to examine results presented in the paper and its supplementary. Contributions include democratising sketch control, introducing an abstraction-aware framework, and leveraging discriminative guidance, validated through extensive experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07234
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle It's All About Your Sketch: Democratising Sketch Control in Diffusion Models
Koley, Subhadeep
Bhunia, Ayan Kumar
Sekhri, Deeptanshu
Sain, Aneeshan
Chowdhury, Pinaki Nath
Xiang, Tao
Song, Yi-Zhe
Computer Vision and Pattern Recognition
This paper unravels the potential of sketches for diffusion models, addressing the deceptive promise of direct sketch control in generative AI. We importantly democratise the process, enabling amateur sketches to generate precise images, living up to the commitment of "what you sketch is what you get". A pilot study underscores the necessity, revealing that deformities in existing models stem from spatial-conditioning. To rectify this, we propose an abstraction-aware framework, utilising a sketch adapter, adaptive time-step sampling, and discriminative guidance from a pre-trained fine-grained sketch-based image retrieval model, working synergistically to reinforce fine-grained sketch-photo association. Our approach operates seamlessly during inference without the need for textual prompts; a simple, rough sketch akin to what you and I can create suffices! We welcome everyone to examine results presented in the paper and its supplementary. Contributions include democratising sketch control, introducing an abstraction-aware framework, and leveraging discriminative guidance, validated through extensive experiments.
title It's All About Your Sketch: Democratising Sketch Control in Diffusion Models
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.07234