5 papers · 1 filter
PhysPlan: Grounded Physical State Reasoning and Graph-Guided Optimization for Physically Plausible Video Generation
Minh-Loi Nguyen, Xuan-Vu Le, Thanh-Toan Do +3
Video diffusion models (VDMs) synthesize photorealistic content, yet they often fail to follow the course that a physical phenomenon should take within a given scene. Recent traini…
PhysMirror: Physics-Aware Mirror Object Generation
Xuan-Bach Mai, Duy-Phuc Nguyen, Quoc-Van Le +6
Synthesizing physically accurate mirror reflections remains a fundamental challenge for modern text-to-image diffusion models, which are increasingly critical for generating synthe…
ShowFlow: From Robust Single Concept to Condition-Free Multi-Concept Generation
Trong-Vu Hoang, Quang-Binh Nguyen, Thanh-Toan Do +3
Customizing image generation remains a core challenge in controllable image synthesis. For single-concept generation, maintaining both identity preservation and prompt alignment is…
CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing
Dinh-Khoi Vo, Thanh-Toan Do, Tam V. Nguyen +2
Editing natural images using textual descriptions in text-to-image diffusion models remains a significant challenge, particularly in achieving consistent generation and handling co…
Multi-Perspective Data Augmentation for Few-shot Object Detection
Anh-Khoa Nguyen Vu, Quoc-Truong Truong, Vinh-Tiep Nguyen +3
Recent few-shot object detection (FSOD) methods have focused on augmenting synthetic samples for novel classes, show promising results to the rise of diffusion models. However, the…