← Search

Qibin Hu

2 accepted papers

2025

Graph2Scene: Versatile 3D Indoor Scene Generation with Interaction-aware Scene Graph

IROS 2025

Embodied artificial intelligence requires a wide variety of large-scale simulated environments for development. Previous scene reconstruction approaches based on multiview images can produce high-fidelity 3D scenes but lack diversity. In contrast, existing prompt-based scene generation approaches ca

Cited by 0SourceScholar
2025

VideoDirector: Precise Video Editing via Text-to-Video Models

CVPR 2025poster

Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion. Consequently, current video editing methods pri…

Cited by 0SourcePDFScholar