StreamErase: Towards Ultra-Fast Streaming Video Erasing
cs.CV
Submitted: 2026-10-14
Updated: 2026-10-14
Project page: https://zhuobaidong.github.io/StreamErase
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Layer Normalization
- VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
- SkyReels-V2: Infinite-length Film Generative Model
- DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution
- EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasing
- Long Context Tuning for Video Generation
- Gaussian Error Linear Units (GELUs)
- VACE: All-in-One Video Creation and Editing
- Auto-Encoding Variational Bayes
- DiffuEraser: A Diffusion Model for Video Inpainting
- PersonaLive! Expressive Portrait Image Animation for Live Streaming
- SDXL-Lightning: Progressive Adversarial Diffusion Distillation
- Diffusion Adversarial Post-Training for One-Step Video Generation
- Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation
- Progressive Distillation for Fast Sampling of Diffusion Models
- MotionStream: Real-Time Video Generation with Interactive Motion Controls
- Improved Techniques for Training Consistency Models
- Consistency Models
- MAGI-1: Autoregressive Video Generation at Scale
- Wan: Open and Advanced Large-Scale Video Generative Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models