Cover Image

FastInit: Fast Noise Initialization for Temporally Consistent Video Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bai, Chengyu, Li, Yuming, Zhao, Zhongyu, Chen, Jintao, Jia, Peidong, She, Qi, Lu, Ming, Zhang, Shanghang
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance
by: Li, Yuming, et al.
Published: (2024)

FreeInit: Bridging Initialization Gap in Video Diffusion Models
by: Wu, Tianxing, et al.
Published: (2023)

UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
by: Bai, Chengyu, et al.
Published: (2025)

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
by: Li, Yuming, et al.
Published: (2025)

InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization
by: Guo, Xiefan, et al.
Published: (2024)

StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
by: Chen, Yilong, et al.
Published: (2025)

Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
by: Li, Qirui, et al.
Published: (2025)

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems
by: Wang, Weijie, et al.
Published: (2026)

ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search
by: Liu, Zhenjie, et al.
Published: (2025)

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning
by: Cao, Jiajun, et al.
Published: (2025)

ManipDreamer3D : Synthesizing Plausible Robotic Manipulation Video with Occupancy-aware 3D Trajectory
by: Li, Ying, et al.
Published: (2025)

Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis
by: Chen, Jintao, et al.
Published: (2026)

AstraNav-World: World Model for Foresight Control and Consistency
by: Chen, Jintao, et al.
Published: (2025)

Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
by: Wang, Yutong, et al.
Published: (2024)

Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
by: Wang, Songping, et al.
Published: (2025)

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
by: Liu, Jiaming, et al.
Published: (2023)

FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing
by: Zhang, Youyuan, et al.
Published: (2024)

DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation
by: Zhang, Runze, et al.
Published: (2025)

ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
by: Zhang, Yuan, et al.
Published: (2025)

Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models
by: Liang, Hanwen, et al.
Published: (2024)

MagCache: Fast Video Generation with Magnitude-Aware Cache
by: Ma, Zehong, et al.
Published: (2025)

Fast Multi-view Consistent 3D Editing with Video Priors
by: Chen, Liyi, et al.
Published: (2025)

PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models
by: Chen, Junsong, et al.
Published: (2024)

Collaborative Temporal Consistency Learning for Point-supervised Natural Language Video Localization
by: Tao, Zhuo, et al.
Published: (2025)

ConceptWeaver: Weaving Disentangled Concepts with Flow
by: Chen, Jintao, et al.
Published: (2026)

FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters
by: Shao, Shitong, et al.
Published: (2026)

Scanning Only Once: An End-to-end Framework for Fast Temporal Grounding in Long Videos
by: Pan, Yulin, et al.
Published: (2023)

EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting
by: Wei, Xiaobao, et al.
Published: (2024)

Diffusion Noise Feature: Accurate and Fast Generated Image Detection
by: Zhang, Yichi, et al.
Published: (2023)

V-CORE: Temporally Consistent Video Understanding for Video-LLM
by: Kang, Zhengjian, et al.
Published: (2026)

InstaVSR: Taming Diffusion for Efficient and Temporally Consistent Video Super-Resolution
by: Hu, Jintong, et al.
Published: (2026)

Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing
by: Su, Tongtong, et al.
Published: (2025)

Fast Video Generation with Sliding Tile Attention
by: Zhang, Peiyuan, et al.
Published: (2025)

FastVID: Dynamic Density Pruning for Fast Video Large Language Models
by: Shen, Leqi, et al.
Published: (2025)

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks
by: Lin, Zuyao, et al.
Published: (2026)

ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting
by: Polyzos, Konstantinos D., et al.
Published: (2025)

EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler
by: Wang, Hao, et al.
Published: (2025)

NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and Collaboration
by: Dong, Haotian, et al.
Published: (2025)

TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
by: Yang, Zuhao, et al.
Published: (2025)

Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks
by: Dedhia, Bhishma, et al.
Published: (2025)