
This paper introduces a novel approach to text-driven video editing that leverages concept pairs (concept prompt and concept video) to enhance the stability and fidelity of video editing results.


coremsg

concept-augmented-video-editing-for-enhanced-stability-and-fidelity


Concept-Augmented Video Editing for Enhanced Stability and Fidelity


title_rewrite


VidEdit is a novel method for zero-shot text-based video editing that guarantees robust temporal and spatial consistency by combining an atlas-based video representation with a pre-trained text-to-image diffusion model.


videdit-zero-shot-and-spatially-aware-text-driven-video-editing


VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing
