ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chang, Di, Cao, Mingdeng, Shi, Yichun, Liu, Bo, Cai, Shengqu, Zhou, Shijie, Huang, Weilin, Wetzstein, Gordon, Soleymani, Mohammad, Wang, Peng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918054449905664
author Chang, Di
Cao, Mingdeng
Shi, Yichun
Liu, Bo
Cai, Shengqu
Zhou, Shijie
Huang, Weilin
Wetzstein, Gordon
Soleymani, Mohammad
Wang, Peng
author_facet Chang, Di
Cao, Mingdeng
Shi, Yichun
Liu, Bo
Cai, Shengqu
Zhou, Shijie
Huang, Weilin
Wetzstein, Gordon
Soleymani, Mohammad
Wang, Peng
contents Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet underexplored problem in computer vision. Existing approaches and datasets predominantly focus on static scenes or rigid transformations, limiting their capacity to handle expressive edits involving dynamic motion. To address this gap, we introduce ByteMorph, a comprehensive framework for instruction-based image editing with an emphasis on non-rigid motions. ByteMorph comprises a large-scale dataset, ByteMorph-6M, and a strong baseline model built upon the Diffusion Transformer (DiT), named ByteMorpher. ByteMorph-6M includes over 6 million high-resolution image editing pairs for training, along with a carefully curated evaluation benchmark ByteMorph-Bench. Both capture a wide variety of non-rigid motion types across diverse environments, human figures, and object categories. The dataset is constructed using motion-guided data generation, layered compositing techniques, and automated captioning to ensure diversity, realism, and semantic coherence. We further conduct a comprehensive evaluation of recent instruction-based image editing methods from both academic and commercial domains.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03107
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions
Chang, Di
Cao, Mingdeng
Shi, Yichun
Liu, Bo
Cai, Shengqu
Zhou, Shijie
Huang, Weilin
Wetzstein, Gordon
Soleymani, Mohammad
Wang, Peng
Computer Vision and Pattern Recognition
Editing images with instructions to reflect non-rigid motions, camera viewpoint shifts, object deformations, human articulations, and complex interactions, poses a challenging yet underexplored problem in computer vision. Existing approaches and datasets predominantly focus on static scenes or rigid transformations, limiting their capacity to handle expressive edits involving dynamic motion. To address this gap, we introduce ByteMorph, a comprehensive framework for instruction-based image editing with an emphasis on non-rigid motions. ByteMorph comprises a large-scale dataset, ByteMorph-6M, and a strong baseline model built upon the Diffusion Transformer (DiT), named ByteMorpher. ByteMorph-6M includes over 6 million high-resolution image editing pairs for training, along with a carefully curated evaluation benchmark ByteMorph-Bench. Both capture a wide variety of non-rigid motion types across diverse environments, human figures, and object categories. The dataset is constructed using motion-guided data generation, layered compositing techniques, and automated captioning to ensure diversity, realism, and semantic coherence. We further conduct a comprehensive evaluation of recent instruction-based image editing methods from both academic and commercial domains.
title ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.03107