MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Godavarthy, Sonali, Neuwirth-Trapp, Matthias, Faasch, Tim-Felix, Bieshaar, Maarten, Moeller, Michael, Paudel, Danda Pani
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917485135003648
author Godavarthy, Sonali
Neuwirth-Trapp, Matthias
Faasch, Tim-Felix
Bieshaar, Maarten
Moeller, Michael
Paudel, Danda Pani
author_facet Godavarthy, Sonali
Neuwirth-Trapp, Matthias
Faasch, Tim-Felix
Bieshaar, Maarten
Moeller, Michael
Paudel, Danda Pani
contents Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There have been a number of recent works dealing with learning and composing multiple objects and patterns. However, current work focuses almost entirely on image content, overlooking imaging factors such as camera lens, sensor types, imaging viewpoints, and scenes' domain characteristics. We introduce this new challenge as Imaging Factor Disentanglement and show limitations of current approaches in the regime. We, therefore, propose the new method Multi-factor disentanglement through Textual Inversion (MULTI). It consists of two stages: in the first stage, we learn general factors, and in the second stage, we extract dataset-specific ones. This setup enables the extension of existing datasets and novel factor combinations, thereby reducing distribution gaps. It further supports modifications of specific factors and image-to-image generation via ControlNets. The evaluation on our new DF-RICO benchmark demonstrates the effectiveness of MULTI and highlights the importance of Factor Disentanglement as a new direction of research.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12134
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation
Godavarthy, Sonali
Neuwirth-Trapp, Matthias
Faasch, Tim-Felix
Bieshaar, Maarten
Moeller, Michael
Paudel, Danda Pani
Computer Vision and Pattern Recognition
Machine Learning
Recent text-to-image models produce high-quality images, yet text ambiguity hinders precise control when specific styles or objects are required. There have been a number of recent works dealing with learning and composing multiple objects and patterns. However, current work focuses almost entirely on image content, overlooking imaging factors such as camera lens, sensor types, imaging viewpoints, and scenes' domain characteristics. We introduce this new challenge as Imaging Factor Disentanglement and show limitations of current approaches in the regime. We, therefore, propose the new method Multi-factor disentanglement through Textual Inversion (MULTI). It consists of two stages: in the first stage, we learn general factors, and in the second stage, we extract dataset-specific ones. This setup enables the extension of existing datasets and novel factor combinations, thereby reducing distribution gaps. It further supports modifications of specific factors and image-to-image generation via ControlNets. The evaluation on our new DF-RICO benchmark demonstrates the effectiveness of MULTI and highlights the importance of Factor Disentanglement as a new direction of research.
title MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.12134