Publications

Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint

Junwei Zhou, Xueting Li, Lu Qi, Ming-Hsuan Yang

Given a text prompt describing multiple objects and their spatial relationships, our method generates a 3D scene depicting these objects naturally interacting with one another.

Full paper: arxiv link

WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition

Lianghui Zhu*, Junwei Zhou*, Yan Liu, Hao Xin, Wenyu Liu, Xinggang Wang

ACM Multimedia 2024

Towards universal weakly-supervised visual perception. Combining Class Activation Maps(CAMs) as classification clues to prompt SAM for weakly-supervised instance-level recognition.

Full paper: arxiv link