Saved in:
Bibliographic Details
Main Authors: Kwon, Young D., Mehrotra, Abhinav, Chadwick, Malcolm, Ramos, Alberto Gil, Bhattacharya, Sourav
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.06295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912634377338880
author Kwon, Young D.
Mehrotra, Abhinav
Chadwick, Malcolm
Ramos, Alberto Gil
Bhattacharya, Sourav
author_facet Kwon, Young D.
Mehrotra, Abhinav
Chadwick, Malcolm
Ramos, Alberto Gil
Bhattacharya, Sourav
contents High-resolution (4K) image-to-image synthesis has become increasingly important for mobile applications. Existing diffusion models for image editing face significant challenges, in terms of memory and image quality, when deployed on resource-constrained devices. In this paper, we present MobilePicasso, a novel system that enables efficient image editing at high resolutions, while minimising computational cost and memory usage. MobilePicasso comprises three stages: (i) performing image editing at a standard resolution with hallucination-aware loss, (ii) applying latent projection to overcome going to the pixel space, and (iii) upscaling the edited image latent to a higher resolution with adaptive context-preserving tiling. Our user study with 46 participants reveals that MobilePicasso not only improves image quality by 18-48% but reduces hallucinations by 14-51% over existing methods. MobilePicasso demonstrates significantly lower latency, e.g., up to 55.8$\times$ speed-up, yet with a small increase in runtime memory, e.g., a mere 9% increase over prior work. Surprisingly, the on-device runtime of MobilePicasso is observed to be faster than a server-based high-resolution image editing model running on an A100 GPU.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06295
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
Kwon, Young D.
Mehrotra, Abhinav
Chadwick, Malcolm
Ramos, Alberto Gil
Bhattacharya, Sourav
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
High-resolution (4K) image-to-image synthesis has become increasingly important for mobile applications. Existing diffusion models for image editing face significant challenges, in terms of memory and image quality, when deployed on resource-constrained devices. In this paper, we present MobilePicasso, a novel system that enables efficient image editing at high resolutions, while minimising computational cost and memory usage. MobilePicasso comprises three stages: (i) performing image editing at a standard resolution with hallucination-aware loss, (ii) applying latent projection to overcome going to the pixel space, and (iii) upscaling the edited image latent to a higher resolution with adaptive context-preserving tiling. Our user study with 46 participants reveals that MobilePicasso not only improves image quality by 18-48% but reduces hallucinations by 14-51% over existing methods. MobilePicasso demonstrates significantly lower latency, e.g., up to 55.8$\times$ speed-up, yet with a small increase in runtime memory, e.g., a mere 9% increase over prior work. Surprisingly, the on-device runtime of MobilePicasso is observed to be faster than a server-based high-resolution image editing model running on an A100 GPU.
title Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2510.06295