MEGA Hub

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction

Authors

Do you know Ziang Zhang?You can claim authorship or link another user.Do you know Wenyou Yi?You can claim authorship or link another user.Do you know Zehan Wang?You can claim authorship or link another user.Do you know Jiachen Xu?You can claim authorship or link another user.Do you know Xintong Han?You can claim authorship or link another user.Do you know Chunchao Guo?You can claim authorship or link another user.Do you know Zhou Zhao?You can claim authorship or link another user.

Abstract

Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle with fine-grained scene geometry and asset quality. Meanwhile, specialized 3D object generators provide detailed object geometry, while 3D foundation models offer strong and generalizable spatial understanding. We propose Easy-3Dfy, a compositional workflow that decouples object generation from scene layout estimation, allowing specialized models to fully exploit their respective strengths. An RPF-based aligner then bridges these capabilities by establishing geometric correspondence between object-local meshes and partial scene pointmaps, recovering object layout for scene composition. Without requiring complete scene-level supervision, the proposed workflow consistently outperforms SAM-3Dfy across multiple geometric metrics on Scene-Maker and 3D-FUTURE200. Our results demonstrate that explicit geometric composition can effectively combine high-quality object generation with strong spatial understanding, while enabling the workflow to benefit independently from advances in both 3D object generation and foundation models.

Community

00