Cover Image

OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Jinshu, Li, Xinghui, Bai, Xu, Ma, Tianxiang, Zhang, Pengze, Chen, Zhuowei, Li, Gen, Liu, Lijie, Zhao, Songtao, Li, Bingchuan, He, Qian
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OmniTransfer: All-in-one Framework for Spatio-temporal Video Transfer
by: Zhang, Pengze, et al.
Published: (2026)

Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset
by: Chen, Zhuowei, et al.
Published: (2025)

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
by: Chen, Liyang, et al.
Published: (2025)

DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation
by: Guo, Xu, et al.
Published: (2026)

Phantom: Subject-consistent video generation via cross-modal alignment
by: Liu, Lijie, et al.
Published: (2025)

AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models
by: Li, Xinghui, et al.
Published: (2024)

HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
by: Li, Mengtian, et al.
Published: (2025)

DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer
by: Guo, Xu, et al.
Published: (2026)

Customize Your Own Paired Data via Few-shot Way
by: Chen, Jinshu, et al.
Published: (2024)

LibraGen: Playing a Balance Game in Subject-Driven Video Generation
by: Zhu, Jiahao, et al.
Published: (2026)

DreamStyle: A Unified Framework for Video Stylization
by: Li, Mengtian, et al.
Published: (2026)

FreeInsert: Personalized Object Insertion with Geometric and Style Control
by: Zhang, Yuhong, et al.
Published: (2025)

InstructX: Towards Unified Visual Editing with MLLM Guidance
by: Mou, Chong, et al.
Published: (2025)

DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning
by: Ye, Fulong, et al.
Published: (2025)

SimInsert: Seamless Video Object Insertion via Regional Sparse Attention Fusion
by: Chen, Xinyu, et al.
Published: (2026)

Point2Insert: Video Object Insertion via Sparse Point Guidance
by: Zhou, Yu, et al.
Published: (2026)

Anything in Any Scene: Photorealistic Video Object Insertion
by: Bai, Chen, et al.
Published: (2024)

EasyInsert: A Data-Efficient and Generalizable Insertion Policy
by: Li, Guanghe, et al.
Published: (2025)

FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors
by: Li, Chenxi, et al.
Published: (2025)

SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer
by: Hui, Zheng, et al.
Published: (2026)

InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion
by: Jin, Hoiyeong, et al.
Published: (2025)

SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers
by: Fei, Zhengcong, et al.
Published: (2025)

Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion
by: He, Jixuan, et al.
Published: (2024)

OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model
by: Chen, Liuhan, et al.
Published: (2024)

Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion
by: Li, Lijiang, et al.
Published: (2026)

Tackling the Singularities at the Endpoints of Time Intervals in Diffusion Models
by: Zhang, Pengze, et al.
Published: (2024)

MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement
by: Deng, Yufan, et al.
Published: (2025)

InsertGNN: Can Graph Neural Networks Outperform Humans in TOEFL Sentence Insertion Problem?
by: Wu, Fang, et al.
Published: (2021)

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation
by: Cheng, Dongjie, et al.
Published: (2026)

VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
by: Liu, Runtao, et al.
Published: (2024)

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing
by: Guo, Zinan, et al.
Published: (2025)

Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model
by: Zhang, Ruixin, et al.
Published: (2025)

Teleportraits: Training-Free People Insertion into Any Scene
by: Gao, Jialu, et al.
Published: (2025)

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
by: Li, Yiheng, et al.
Published: (2026)

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
by: Zhao, Min, et al.
Published: (2025)

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model
by: Yang, Yang, et al.
Published: (2025)

DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single Image
by: Zhao, Qi, et al.
Published: (2025)

Any-Order Flexible Length Masked Diffusion
by: Kim, Jaeyeon, et al.
Published: (2025)

Omni-Referring Image Segmentation
by: Zheng, Qiancheng, et al.
Published: (2025)

Insert Anything: Image Insertion via In-Context Editing in DiT
by: Song, Wensong, et al.
Published: (2025)