Efficient Part-level 3D Object Generation via Dual Volume Packing
This addresses the limitation of fused mesh generation for 3D object editing and manipulation, offering a domain-specific improvement for computer graphics and 3D modeling applications.
The paper tackles the problem of generating 3D objects with editable parts from a single image, proposing a dual volume packing strategy that produces high-quality objects with arbitrary numbers of semantically meaningful parts, achieving better quality, diversity, and generalization than previous methods.
Recent progress in 3D object generation has greatly improved both the quality and efficiency. However, most existing methods generate a single mesh with all parts fused together, which limits the ability to edit or manipulate individual parts. A key challenge is that different objects may have a varying number of parts. To address this, we propose a new end-to-end framework for part-level 3D object generation. Given a single input image, our method generates high-quality 3D objects with an arbitrary number of complete and semantically meaningful parts. We introduce a dual volume packing strategy that organizes all parts into two complementary volumes, allowing for the creation of complete and interleaved parts that assemble into the final object. Experiments show that our model achieves better quality, diversity, and generalization than previous image-based part-level generation methods.