FlashWorld: High-quality 3D Scene Generation within Seconds

ICLROral2026

Authors
Xinyang Li, Tengfei Wang, Zixiao Gu, Shengchuan Zhang, Chunchao Guo, Liujuan Cao
Affiliation
Xiamen University
Venue
ICLR 2026
Track
Oral

TL;DR

a generative model that produces high-quality 3D scenes from a single image or text prompt in seconds…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

generative model 3d

Related ICLR papers

← All ICLR 2026 Oral papers · Browse the whole archive