GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence

TL;DR

GENA3D introduces a novel framework that combines 2D generative priors with 3D geometric reasoning to produce complete, plausible, and coherent 3D objects from partial observations, addressing a key challenge in amodal 3D modeling.

Contribution

The paper proposes GENA3D, a new method that effectively integrates 2D priors with 3D structural constraints for amodal 3D object generation, ensuring both plausibility and geometric consistency.

Findings

Outperforms existing methods in synthetic scenarios.

Achieves better results in real-world amodal tasks.

Ensures multi-view consistency and spatial validity.

Abstract

Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either operate directly in 3D, which ensures geometric consistency but often lacks generative expressiveness, or rely on 2D amodal completion, which provides strong appearance priors but does not guarantee reliable 3D structure. This raises a key question: how can we achieve both generative plausibility and geometric coherence in amodal 3D modeling? To answer this question, we introduce GENA3D (GENarative Amodal 3D), a framework that integrates learned 2D generative priors with explicit 3D geometric reasoning within a conditional 3D generation paradigm. The 2D priors enable the model to plausibly infer diverse occluded content, while the 3D representation enforces multi-view consistency and spatial validity. Our design incorporates a novel View-Wise Cross-Attention for multi-view alignment and a Stereo-Conditioned Cross-Attention to anchor generative predictions in 3D relationships. By combining generative imagination with structural constraints, GENA3D generates complete and coherent 3D objects from limited observations without sacrificing geometric fidelity. Experiments demonstrate that our method outperforms existing approaches in both synthetic and real-world amodal scenarios, highlighting the effectiveness of bridging 2D priors and 3D coherence in generating plausible and geometrically consistent 3D structures in complex environments.