AI Insight
BrickAnything is an AI system that automatically generates physically buildable LEGO-like brick structures from 3D shapes using a geometry-conditioned autoregressive framework. The system introduces a structure-aware tree tokenization method that represents brick structures through local attachment relations, making the generation process more aligned with actual physical construction and reducing invalid intermediate states. Experiments demonstrate the approach produces geometrically accurate and structurally stable brick assemblies while significantly reducing the need for rollback and regeneration compared to conventional methods.
Why it matters
This research could streamline the design process for brick-based construction toys, architectural models, and educational tools by automating the translation of digital 3D models into physically buildable structures. The method's focus on structural stability and assembly constraints makes it practical for real-world applications where physical realizability is essential.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Generating physically buildable brick structures from 3D shapes requires more than geometric reconstruction: the output must also satisfy discrete part constraints and structural stability. Existing brick generation methods either rely on heuristic optimization, which can break down when the target 3D shape does not admit a feasible structure under predefined constraints, or generate brick sequences without explicitly modeling the underlying 3D geometry and assembly relations. In this work, we present BrickAnything, a geometry-conditioned autoregressive framework for generating buildable brick structures from diverse 3D representations. BrickAnything uses point clouds as a unified geometric interface and predicts brick sequences that reconstruct the target shape under assembly constraints. To model structural dependencies among bricks, we introduce a structure-aware tree tokenization, which represents brick structures through local attachment relations. This formulation makes sequence generation more consistent with the physical construction process, and reduces invalid intermediate states. We further introduce preference-based alignment post-training, validity-constrained decoding and adaptive rollback to improve buildability objectives such as stability and geometric fidelity. Extensive experiments demonstrate that BrickAnything produces geometrically faithful and physically realizable brick structures, and that the proposed tokenization effectively reduces rollback and regeneration compared with conventional ordering strategies.
Source: BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Tokenization