StyleFields: Multi-Scale AdaIN-Modulated Implicit SDFs for Coarse-to-Fine 3D Shape Reconstruction and Editing

2026-10-06

AI Summary

This study addresses the challenge of controllable geometric style blending in high-fidelity 3D reconstruction by proposing an unsupervised content-style disentanglement method based on DeepSDF. By injecting latent codes via multi-scale Adaptive Instance Normalization (AdaIN) alongside a depth-aware modulation mechanism, and integrating coarse-to-fine supervision with a progressive depth growth strategy, the approach effectively separates global shapes from high-frequency details without requiring part labels or adversarial training. Experimental results demonstrate that the proposed method achieves precise reconstruction and realistic style blending. Furthermore, its effectiveness for directional editing is validated in automotive aerodynamic design by freezing complementary latent code streams.

Abstract

We introduce StyleFields, a DeepSDF-based architecture for high-fidelity 3D reconstruction that enables controllable geometric style mixing: the coarse structure of one object can be combined with the fine-scale details of another. The core idea is depth-aware modulation: instead of a single global code, we inject latents via multi-level Adaptive Instance Normalization at several decoder depths, and supervise matching auxiliary heads with a coarse-to-fine schedule while gradually growing network depth. This aligns early layers with global shape and later layers with high-frequency detail, achieving content-style decoupling without part labels or adversarial training. StyleFields delivers faithful reconstructions, convincing cross-instance hybrids, and consistent gains in ablations over injection depth and supervision granularity. We further demonstrate a practical application in automotive aerodynamics: a learned surrogate drag predictor serves as a differentiable objective to optimize reconstructed cars, allowing targeted edits of global form or surface details by freezing the complementary latent stream. StyleFields offers a simple, effective recipe for controllable implicit reconstruction and downstream performance-driven design.

Problem

• 3D shape reconstruction
• geometric style mixing
• content-style decoupling
• implicit SDFs
• shape editing

Innovation

• Implicit SDFs
• Multi-Scale AdaIN
• Coarse-to-Fine Reconstruction
• Geometric Style Mixing
• Differentiable Surrogate