# Pose-Aware Diffusion for 3D Generation Source: [Pose-Aware Diffusion for 3D Generation]() Collection index: [llms.txt]() Data updated: 2026-05-05T05:00:04.460Z Authors: Zihan Zhou, Luxi Chen, Jingzhi Zhou, Yuhao Wan, Min Zhao, Baoyu Fan, Chongxuan Li Published: 2026-05-01T02:05:28.000Z ## Abstract Generating pose-aligned 3D objects is challenging due to the spatial mismatches and transformation ambiguities inherent in decoupled canonical-then-rotate paradigms. To this end, we introduce Pose-Aware Diffusion (PAD), a novel end-to-end diffusion framework that synthesizes 3D geometry directly within the observation space. By unprojecting monocular depth into a partial point cloud and explicitly injecting it as a 3D geometric anchor, PAD abandons canonical assumptions to enforce rigorous spatial supervision. This native generation intrinsically resolves pose ambiguity, producing high-fidelity pose-aligned assets. Extensive experiments demonstrate that PAD achieves superior geometric alignment and image-to-3D correspondence compared to state-of-the-art methods. Additionally, PAD naturally extends to compositional 3D scene reconstruction via a simple union of independently generated objects, highlighting its robust ability to preserve precise spatial layouts. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Posed Object Generation on Google Scanned Objects (GSO) (test)](): Posed Object Generation; Google Scanned Objects (GSO) (test); CD (Chamfer Distance): 48.76. - [Compositional 3D Scene Generation on 3D-FUTURE first 200 scenes (test)](): Compositional 3D Scene Generation; 3D-FUTURE first 200 scenes (test); Chamfer Distance (CD): 56240. ## Original sources and implementation [Original paper]() [PDF]()