arXiv:2608.09597cs.CV2026-08

从照片生成可手工搭建的砖块模型,兼顾外观相似与结构稳定。

ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability

论文配图:ResemBrick: Brick Reconstruction from Photographs with Perceptual Fidelity and Buildability
图 1 · 摘自论文原文
  • 将体素化视为可优化的分配问题,统一处理外观与可构建性
  • 在相同预算下,实现零悬浮砖块和零不稳砖块,感知保真度更高
  • 适合需要高保真且可物理搭建3D模型的创意设计场景

从几张随意拍摄的照片生成一个可手工搭建、带颜色的砖块3D模型,是解决更广泛挑战的一个理想测试:在离散、预算有限的体素网格下生成满足物理组装约束的3D内容。在粗粒度网格上,视觉相似性和结构稳定性相互制约,而以往方法仅关注其中一端,且将体素化视为固定预处理步骤。我们提出ResemBrick,将二者紧密耦合。预算约束下的体素填充重构了离散化过程:给定目标占用体素数量,一个单一分辨率条件网络在一次前向传播中决定哪些表面体素应被填充,一套权重覆盖13种分辨率。通过构建保证的可构建性,结合支持感知与前瞻感知的贪心放置策略,以及确定性的、可证明终止的修复机制,确保每个悬浮部件都被稳固支撑。在相同预算下,ResemBrick在感知保真度上超越现有体素选择器,且首次在未过滤的测试对象上实现零悬浮与零不稳定砖块;作为完整管线,其感知保真度优于所有既有砖块构建系统。结果表明,应将离散化与组装阶段视为紧密耦合而非独立过程。

原文摘要 · Abstract (English)

Producing a hand-buildable, colored brick model of a 3D object from a few casual photographs is a clean testbed for a broader challenge: generating 3D content that meets hard physical-assembly constraints under a discrete, budget-limited voxel grid. On a coarse lattice, visual resemblance and structural stability pull against each other, yet prior brick pipelines address only one side and treat voxelization as fixed preprocessing rather than a variable to optimize. We present ResemBrick, which couples the two. Budgeted occupancy completion reframes discretization as allocation: given a target occupied-voxel count, a single resolution-conditioned network decides in one feed-forward pass which surface voxels to fill for best appearance, one weight set spanning 13 resolutions. Buildability by construction then combines support- and look-ahead-aware greedy placement with a deterministic, provably terminating repair that grounds every floating component. Under a matched budget, ResemBrick surpasses existing voxel selectors in perceptual fidelity while uniquely reaching zero floating and zero unstable bricks on unfiltered held-out objects; as a complete pipeline, it attains the best perceptual fidelity among prior brick-construction systems. Our results point to treating discretization and assembly as tightly coupled stages rather than independent ones.

3D重建可构建性体素优化图像生成

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。