Pith. sign in

REVIEW 1 cited by

DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.12796 v1 pith:6WUX5DNT submitted 2024-05-21 cs.CV

classification cs.CV
keywords customizeddisenstudiogenerationmulti-subjectsubjectsubjectstuningexisting
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Generating customized content in videos has received increasing attention recently. However, existing works primarily focus on customized text-to-video generation for single subject, suffering from subject-missing and attribute-binding problems when the video is expected to contain multiple subjects. Furthermore, existing models struggle to assign the desired actions to the corresponding subjects (action-binding problem), failing to achieve satisfactory multi-subject generation performance. To tackle the problems, in this paper, we propose DisenStudio, a novel framework that can generate text-guided videos for customized multiple subjects, given few images for each subject. Specifically, DisenStudio enhances a pretrained diffusion-based text-to-video model with our proposed spatial-disentangled cross-attention mechanism to associate each subject with the desired action. Then the model is customized for the multiple subjects with the proposed motion-preserved disentangled finetuning, which involves three tuning strategies: multi-subject co-occurrence tuning, masked single-subject tuning, and multi-subject motion-preserved tuning. The first two strategies guarantee the subject occurrence and preserve their visual attributes, and the third strategy helps the model maintain the temporal motion-generation ability when finetuning on static images. We conduct extensive experiments to demonstrate our proposed DisenStudio significantly outperforms existing methods in various metrics. Additionally, we show that DisenStudio can be used as a powerful tool for various controllable generation applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

    cs.CV 2025-02 conditional novelty 5.0 of 10

    A tuning-free multi-concept video personalization method that uses anchored prompt tokens and per-reference concept embeddings to prevent identity blending.

Pith tools