DecompDreamer: A Composition-Aware Curriculum for Structured 3D Asset Generation
This addresses a fundamental bottleneck in text-to-3D generation for applications requiring complex scenes, though it is incremental as it builds on existing optimization frameworks.
The paper tackles the problem of generating compositional 3D assets from text, where existing methods fail due to conflicting gradients, and introduces DecompDreamer, which outperforms state-of-the-art methods in fidelity, disentanglement, and spatial coherence.
Current text-to-3D methods excel at generating single objects but falter on compositional prompts. We argue this failure is fundamental to their optimization schedules, as simultaneous or iterative heuristics predictably collapse under a combinatorial explosion of conflicting gradients, leading to entangled geometry or catastrophic divergence. In this paper, we reframe the core challenge of compositional generation as one of optimization scheduling. We introduce DecompDreamer, a framework built on a novel staged optimization strategy that functions as an implicit curriculum. Our method first establishes a coherent structural scaffold by prioritizing inter-object relationships before shifting to the high-fidelity refinement of individual components. This temporal decoupling of competing objectives provides a robust solution to gradient conflict. Qualitative and quantitative evaluations on diverse compositional prompts demonstrate that DecompDreamer outperforms state-of-the-art methods in fidelity, disentanglement, and spatial coherence.