TopoCtrl: Post-Optimization Topology Editing Toward Target Structural Characteristics

2026-03-27

AI Summary

This work addresses the challenge of controllably editing topology optimization results according to discrete or non-smooth structural attributes—such as member thickness or node count—by introducing a post-optimization control framework based on latent diffusion models. The proposed method uniquely integrates lightweight regression guidance with a partial noising strategy to explicitly steer target features within the latent space of a pre-trained topology foundation model, eliminating the need for task-specific re-optimization or manual sensitivity analysis. Experimental results demonstrate that the approach accurately generates designs meeting specified structural criteria across diverse editing tasks, substantially outperforming indirect parameter tuning or geometric post-processing techniques while preserving structural coherence and faithfully retaining the original design intent.

Abstract

Topology optimization can generate high-performance structures, but designers often need to revise the resulting topology in ways that reflect fabrication preferences, structural intuition, or downstream design constraints. In particular, they may wish to explicitly control interpretable structural characteristics such as member thickness, characteristic member length, the number of joints, or the number of members connected to a joint. These quantities are often discrete, non-smooth, or only available through a forward evaluation procedure, making them difficult to impose within conventional optimization pipelines. We present TopoCtrl, a post-optimization control framework that repurposes the latent space of a pre-trained topology foundation model for explicit characteristic-guided editing. Given an optimized topology, TopoCtrl encodes it into the latent space of a latent diffusion model, applies partial noising to preserve instance similarity while creating room for modification, and then performs regression-guided denoising toward a prescribed target characteristic. The concept is to train a lightweight regression model on latent representations annotated with evaluated structural characteristics, and to use its gradient as a differentiable guidance signal during reverse diffusion. This avoids the need for characteristic-specific reformulations, hand-derived sensitivities, or iterative optimization. Because the method operates through partial noising of an existing topology latent, it preserves overall structural similarity while still enabling characteristic controls. Across representative control tasks involving both continuous and discrete structural characteristics, TopoCtrl produces target-aligned topology modifications while better preserving structural coherence and design intent than indirect parameter tuning or naive geometric post-processing.

Problem

• topology optimization
• structural characteristics
• post-optimization editing
• design control
• latent space

Innovation

• topology editing
• latent diffusion model
• structural characteristics control
• post-optimization
• gradient-guided denoising