Saved in:
Bibliographic Details
Main Authors: Singh, Shivam, Chen, Yiming, Chatterjee, Agneet, Raj, Amit, Hays, James, Yang, Yezhou, Baral, Chitta
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.18083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915569197907968
author Singh, Shivam
Chen, Yiming
Chatterjee, Agneet
Raj, Amit
Hays, James
Yang, Yezhou
Baral, Chitta
author_facet Singh, Shivam
Chen, Yiming
Chatterjee, Agneet
Raj, Amit
Hays, James
Yang, Yezhou
Baral, Chitta
contents Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18083
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Chimera: Compositional Image Generation using Part-based Concepting
Singh, Shivam
Chen, Yiming
Chatterjee, Agneet
Raj, Amit
Hays, James
Yang, Yezhou
Baral, Chitta
Computer Vision and Pattern Recognition
Personalized image generative models are highly proficient at synthesizing images from text or a single image, yet they lack explicit control for composing objects from specific parts of multiple source images without user specified masks or annotations. To address this, we introduce Chimera, a personalized image generation model that generates novel objects by combining specified parts from different source images according to textual instructions. To train our model, we first construct a dataset from a taxonomy built on 464 unique (part, subject) pairs, which we term semantic atoms. From this, we generate 37k prompts and synthesize the corresponding images with a high-fidelity text-to-image model. We train a custom diffusion prior model with part-conditional guidance, which steers the image-conditioning features to enforce both semantic identity and spatial layout. We also introduce an objective metric PartEval to assess the fidelity and compositional accuracy of generation pipelines. Human evaluations and our proposed metric show that Chimera outperforms other baselines by 14% in part alignment and compositional accuracy and 21% in visual quality.
title Chimera: Compositional Image Generation using Part-based Concepting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.18083