Imagen de Portada

DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wang, Wenchuan, Huang, Mengqi, Tu, Yijing, Mao, Zhendong
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
por: Lin, Yijing, et al.
Publicado: (2025)

Stream-T1: Test-Time Scaling for Streaming Video Generation
por: Tu, Yijing, et al.
Publicado: (2026)

Gradual Residuals Alignment: A Dual-Stream Framework for GAN Inversion and Image Attribute Editing
por: Li, Hao, et al.
Publicado: (2024)

RealCustom: Narrowing Real Text Word for Real-Time Open-Domain Text-to-Image Customization
por: Huang, Mengqi, et al.
Publicado: (2024)

Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models
por: Liu, Huijie, et al.
Publicado: (2025)

RealCustom++: Representing Images as Real Textual Word for Real-Time Customization
por: Mao, Zhendong, et al.
Publicado: (2024)

Magic-Me: Identity-Specific Video Customized Diffusion
por: Ma, Ze, et al.
Publicado: (2024)

Nearly Lossless Adaptive Bit Switching
por: Huang, Haiduo, et al.
Publicado: (2025)

MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching
por: Wu, Yen-Siang, et al.
Publicado: (2025)

FMA-Net++: Motion- and Exposure-Aware Real-World Joint Video Super-Resolution and Deblurring
por: Youk, Geunhyuk, et al.
Publicado: (2025)

JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation
por: Chen, Fangda, et al.
Publicado: (2025)

Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior
por: Mahmud, Tanvir, et al.
Publicado: (2024)

Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commenting
por: Fu, Fengyi, et al.
Publicado: (2024)

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
por: Guo, Mengqi, et al.
Publicado: (2025)

DualComp: End-to-End Learning of a Unified Dual-Modality Lossless Compressor
por: Zhao, Yan, et al.
Publicado: (2025)

Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models
por: Li, Chao, et al.
Publicado: (2025)

COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection
por: Peng, Peiran, et al.
Publicado: (2025)

Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
por: Han, Gyojin, et al.
Publicado: (2026)

SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning
por: Wang, Futian, et al.
Publicado: (2025)

MambaOVSR: Multiscale Fusion with Global Motion Modeling for Chinese Opera Video Super-Resolution
por: Chang, Hua, et al.
Publicado: (2025)

More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
por: Tian, Xinyu, et al.
Publicado: (2025)

Towards Lossless Ultimate Vision Token Compression for VLMs
por: Zheng, Dehua, et al.
Publicado: (2025)

VideoRouter: Query-Adaptive Dual Routing for Efficient Long-Video Understanding
por: Lin, Kuanwei, et al.
Publicado: (2026)

Zero-Shot Monocular Motion Segmentation in the Wild by Combining Deep Learning with Geometric Motion Model Fusion
por: Huang, Yuxiang, et al.
Publicado: (2024)

RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
por: Chen, Aiyue, et al.
Publicado: (2025)

DepthMamba with Adaptive Fusion
por: Meng, Zelin, et al.
Publicado: (2024)

Towards Fine-Grained Human Motion Video Captioning
por: Song, Guorui, et al.
Publicado: (2025)

Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding
por: Lai, Yixuan, et al.
Publicado: (2026)

LINR-PCGC: Lossless Implicit Neural Representations for Point Cloud Geometry Compression
por: Huang, Wenjie, et al.
Publicado: (2025)

CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization
por: Chen, Nan, et al.
Publicado: (2024)

FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding
por: Tu, Chongjun, et al.
Publicado: (2025)

LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
por: Sun, Boyuan, et al.
Publicado: (2025)

CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
por: Dang, Yunkai, et al.
Publicado: (2026)

PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
por: Huang, Yidong, et al.
Publicado: (2026)

Adaptive Image Restoration for Video Surveillance: A Real-Time Approach
por: Amin, Muhammad Awais, et al.
Publicado: (2025)

Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations
por: Dong, Xiaoxiang, et al.
Publicado: (2025)

MagicFace: Training-free Universal-Style Human Image Customized Synthesis
por: Wang, Yibin, et al.
Publicado: (2024)

X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents
por: Song, Guoxian, et al.
Publicado: (2025)

Towards Efficient Real-Time Video Motion Transfer via Generative Time Series Modeling
por: Haque, Tasmiah, et al.
Publicado: (2025)

I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength
por: Feng, Wanquan, et al.
Publicado: (2024)