Copertina

Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Dohun, Jeong, Hyeonho, Kim, Jiwook, Ceylan, Duygu, Ye, Jong Chul
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing
di: Lee, Dohun, et al.
Pubblicazione: (2026)

Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
di: Jeong, Hyeonho, et al.
Pubblicazione: (2024)

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
di: Jeong, Hyeonho, et al.
Pubblicazione: (2023)

VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide
di: Lee, Dohun, et al.
Pubblicazione: (2024)

Reangle-A-Video: 4D Video Generation as Video-to-Video Translation
di: Jeong, Hyeonho, et al.
Pubblicazione: (2025)

Spectral Motion Alignment for Video Motion Transfer using Diffusion Models
di: Park, Geon Yeong, et al.
Pubblicazione: (2024)

TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation
di: Kwon, Gihyun, et al.
Pubblicazione: (2024)

DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing
di: Jeong, Hyeonho, et al.
Pubblicazione: (2024)

ACDC: Autoregressive Coherent Multimodal Generation using Diffusion Correction
di: Chung, Hyungjin, et al.
Pubblicazione: (2024)

Optical-Flow Guided Prompt Optimization for Coherent Video Generation
di: Nam, Hyelin, et al.
Pubblicazione: (2024)

JOG3R: Towards 3D-Consistent Video Generators
di: Huang, Chun-Hao Paul, et al.
Pubblicazione: (2025)

Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM
di: Kim, Jaemin, et al.
Pubblicazione: (2024)

PromptLoop: Plug-and-Play Prompt Refinement via Latent Feedback for Diffusion Model Alignment
di: Lee, Suhyeon, et al.
Pubblicazione: (2025)

Representation Alignment for Just Image Transformers is not Easier than You Think
di: Shin, Jaeyo, et al.
Pubblicazione: (2026)

Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion
di: Park, Jangho, et al.
Pubblicazione: (2025)

InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems
di: Elata, Noam, et al.
Pubblicazione: (2025)

Scribble-Guided Diffusion for Training-free Text-to-Image Generation
di: Lee, Seonho, et al.
Pubblicazione: (2024)

Boosting Camera Motion Control for Video Diffusion Transformers
di: Cheong, Soon Yau, et al.
Pubblicazione: (2024)

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models
di: Lee, Jaa-Yeon, et al.
Pubblicazione: (2026)

MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding
di: Han, Inhwa, et al.
Pubblicazione: (2024)

Solving Video Inverse Problems Using Image Diffusion Models
di: Kwon, Taesung, et al.
Pubblicazione: (2024)

GeoFusionLRM: Geometry-Aware Self-Correction for Consistent 3D Reconstruction
di: Yildirim, Ahmet Burak, et al.
Pubblicazione: (2026)

Class-Continuous Conditional Generative Neural Radiance Field
di: Kim, Jiwook, et al.
Pubblicazione: (2023)

Self-Guided Generation of Minority Samples Using Diffusion Models
di: Um, Soobin, et al.
Pubblicazione: (2024)

ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models
di: Kara, Ozgur, et al.
Pubblicazione: (2025)

VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models
di: Kwon, Taesung, et al.
Pubblicazione: (2024)

ContextMRI: Enhancing Compressed Sensing MRI through Metadata Conditioning
di: Chung, Hyungjin, et al.
Pubblicazione: (2025)

EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation
di: Vandersanden, Jente, et al.
Pubblicazione: (2026)

Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models
di: Jeon, Wooseok, et al.
Pubblicazione: (2026)

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
di: Kim, Bryan Sangwoo, et al.
Pubblicazione: (2025)

RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection
di: Lee, Junhee, et al.
Pubblicazione: (2025)

ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler
di: Yang, Serin, et al.
Pubblicazione: (2024)

MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection
di: Yildirim, Ahmet Burak, et al.
Pubblicazione: (2025)

Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection
di: Kwon, Gihyun, et al.
Pubblicazione: (2024)

Contrastive CFG: Improving CFG in Diffusion Models by Contrasting Positive and Negative Concepts
di: Chang, Jinho, et al.
Pubblicazione: (2024)

Latent Schrodinger Bridge: Prompting Latent Diffusion for Fast Unpaired Image-to-Image Translation
di: Kim, Jeongsol, et al.
Pubblicazione: (2024)

Training-Free Reward-Guided Image Editing via Trajectory Optimal Control
di: Chang, Jinho, et al.
Pubblicazione: (2025)

Gradient-Free Noise Optimization for Reward Alignment in Generative Models
di: Kim, Jeongsol, et al.
Pubblicazione: (2026)

SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder
di: Lee, Jaeseong, et al.
Pubblicazione: (2024)

Don't Play Favorites: Minority Guidance for Diffusion Models
di: Um, Soobin, et al.
Pubblicazione: (2023)