Tabletop Scene Synthesis via Diffusion Models
Qihuang Zheng, Jiamin Xu · 2024
Tabletop scene synthesis is an important but underexplored area in scene generation. Existing methods typically focus on larger furniture pieces, often neglecting the fine-grained details of smaller objects positioned on surfaces like tabletops. To address this gap, we propose the first method specifically designed for tabletop scene synthesis using a diffusion model. Our diffusion model, trained on a large dataset of tabletop scenes, achieves state-of-the-art performance compared to current scene generation methods.