A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos
cs.CV, cs.MM
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing
- Wan: Open and Advanced Large-Scale Video Generative Models
- Open-Sora Plan: Open-Source Large Video Generation Model
- Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
- Denoising Diffusion Implicit Models
- Flow Matching for Generative Modeling
- Generative Latent Video Compression
- Generative Video Compression with One-Dimensional Latent Representation
- GVC-RT: Towards Real-Time Generative Video Compression at Ultra-Low Bitrates
- ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling
- DiffVC-OSD: One-Step Diffusion-based Perceptual Neural Video Compression Framework
- DiffVC-RT: Towards Practical Real-Time Diffusion-based Perceptual Neural Video Compression
- Free-GVC: Towards Training-Free Extreme Generative Video Compression with Temporal Coherence
- GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow
- ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors
- Stable Diffusion is a Natural Cross-Modal Decoder for Layered AI-generated Image Compression
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- Compressed Image Generation with Denoising Diffusion Codebook Models
- MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection
- Kling-Omni Technical Report
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