OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models
Authors:
- 1 June 2026
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4067-4077
Abstract
No abstract availableThis publication has 20 references indexed in Scilit:
- Multi-subject Open-set Personalization in Video Generation2025
- Koala-36M : A Large-Scale Video Dataset Improving Consistency between Fine-Grained Conditions and Video Content2025
- DragVideo: Interactive Drag-Style Video Editing2024
- CCEdit: Creative and Controllable Video Editing via Diffusion Models2024
- Diffusion Model Alignment Using Direct Preference Optimization2024
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis2024
- MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model2024
- Scalable Diffusion Models with Transformers2023
- DVI: Depth Guided Video Inpainting for Autonomous Driving2020
- ArcFace: Additive Angular Margin Loss for Deep Face Recognition2019