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

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

3 Jun 2025arXiv:2506.03107archive 2025-07-28

Di Chang, Mingdeng Cao, Yichun Shi, Bo Liu, Shengqu Cai, Shijie Zhou, Weilin Huang, Gordon Wetzstein, Mohammad Soleymani, Peng Wang

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bytedance-seed/bm-code officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

BenchmarkingDiversity

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsBPEDense ConnectionsDiffusionDropoutFocusLabel SmoothingLayer NormalizationSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections