3 papers
cs.CV2026
Inclusive Interactive Collisions for Multi-View Consistent Compositional 3D Generation
Chang Liu, Mingwen Shao, Xiang Lv +5
Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model. However, existing methods remain two practical challenges: (1) Th…
cs.CV2026
StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives
Jinghao Hu, Yuhe Zhang, GuoHua Geng +2
Generating multi-frame, action-rich visual narratives without fine-tuning faces a threefold tension: action text faithfulness, subject identity fidelity, and cross-frame background…
cs.CV2024
Beyond Color and Lines: Zero-Shot Style-Specific Image Variations with Coordinated Semantics
Jinghao Hu, Yuhe Zhang, GuoHua Geng +5
Traditionally, style has been primarily considered in terms of artistic elements such as colors, brushstrokes, and lighting. However, identical semantic subjects, like people, boat…