Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |