用正负超二次曲面实现紧凑结构化3D重建，支持精准挖洞与凹陷建模。
DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives
- 采用正负超二次曲面的加减混合建模，提升形状表达能力。
- 在多视角图像上端到端训练，重建精度达当前最优，输出模型体积小且结构清晰。
- 适合需要可编辑、可动画的3D资产场景，如游戏与工业设计。
神经3D重建常在结构与保真度间权衡，生成密集无序网格，拓扑不规则且部件边界模糊，不利于编辑、动画及下游资产复用。本文提出DualPrim，一种紧凑且结构化的3D重建框架。不同于仅加法的隐式或基元方法，DualPrim使用正负超二次曲面：前者构建主体，后者通过可微运算器实现局部体积雕刻，从而感知拓扑地建模孔洞与凹陷。该加减结合设计在不牺牲紧凑性与可微性的前提下增强表达力。我们将DualPrim嵌入体素可微渲染器，实现从多视角图像的端到端学习，并通过闭式布尔差分无缝导出网格。实验表明，DualPrim达到当前最优精度，输出紧凑、结构化且可解释，显著优于仅加法的替代方案。
原文摘要 · Abstract (English)
Neural reconstructions often trade structure for fidelity, yielding dense and unstructured meshes with irregular topology and weak part boundaries that hinder editing, animation, and downstream asset reuse. We present DualPrim, a compact and structured 3D reconstruction framework. Unlike additive-only implicit or primitive methods, DualPrim represents shapes with positive and negative superquadrics: the former builds the bases while the latter carves local volumes through a differentiable operator, enabling topology-aware modeling of holes and concavities. This additive-subtractive design increases the representational power without sacrificing compactness or differentiability. We embed DualPrim in a volumetric differentiable renderer, enabling end-to-end learning from multi-view images and seamless mesh export via closed-form boolean difference. Empirically, DualPrim delivers state-of-the-art accuracy and produces compact, structured, and interpretable outputs that better satisfy downstream needs than additive-only alternatives.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。