Xinyang Li 李新阳

FlashWorld. Code for "FlashWorld: High-quality 3D Scene Generation within Seconds" (ICLR 2026 Oral)

HiSD. Code for "Image-to-image Translation via Hierarchical Style Disentanglement" (CVPR 2021 Oral).

Director3D. Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text" (NeurIPS 2024).

AGUIT. Pytorch Implementation of Paper ‘’Attribute Guided Unpaired Image-to-image Translation with Semi-supervised Learning"

SynergyAmodal. Code, Dataset, and Models for "SynergyAmodal: Deocclude Anything with Text Control" (ACMMM 2025)

FlashWorld_Page. HTML