Hugging Face Daily Papers·· 24 days agoAI score25
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-view Images
OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images
AI briefing
OmniShowcase proposes a method for generating omnidirectional subject-consistent videos from multi-view images, achieving subject consistency under 360-degree surrounding viewpoints through automatic data synthesis and geometric conditioning. Experiments show it achieves state-of-the-art in subject identity and 3D consistency while maintaining competitive video quality and motion. The research also constructs the Showcase-4K dataset (12 camera motions, 88 trajectory configurations) and the ShowcaseBench evaluation set.
Open original arxiv.org