Thinking Like Van Gogh: Structure-Aware Style Transfer via Flow-Guided 3D Gaussian Splatting

2026-01-15

AI Summary

This work addresses the limitations of existing 3D style transfer methods, which treat geometry as a rigid scaffold and thus fail to capture the structural exaggeration and geometric abstraction characteristic of Post-Impressionist art. To overcome this, we propose a mesh-free, flow-guided mechanism that extracts directional flow fields from 2D paintings and back-projects them into 3D space to drive the deformation of 3D Gaussians along artistic brushstrokes. Concurrently, a luminance-structure decoupling strategy is introduced to separately optimize color and geometric deformation. To quantitatively assess artistic fidelity, we construct an evaluation framework based on vision-language models (VLMs). Experiments demonstrate that our approach generates 3D scenes aligned with Post-Impressionist aesthetics, enhancing structural expressiveness while effectively mitigating artifacts commonly observed in conventional methods.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In 1888, Vincent van Gogh wrote,"I am seeking exaggeration in the essential."This principle, amplifying structural form while suppressing photographic detail, lies at the core of Post-Impressionist art. However, most existing 3D style transfer methods invert this philosophy, treating geometry as a rigid substrate for surface-level texture projection. To authentically reproduce Post-Impressionist stylization, geometric abstraction must be embraced as the primary vehicle of expression. We propose a flow-guided geometric advection framework for 3D Gaussian Splatting (3DGS) that operationalizes this principle in a mesh-free setting. Our method extracts directional flow fields from 2D paintings and back-propagates them into 3D space, rectifying Gaussian primitives to form flow-aligned brushstrokes that conform to scene topology without relying on explicit mesh priors. This enables expressive structural deformation driven directly by painterly motion rather than photometric constraints. Our contributions are threefold: (1) a projection-based, mesh-free flow guidance mechanism that transfers 2D artistic motion into 3D Gaussian geometry; (2) a luminance-structure decoupling strategy that isolates geometric deformation from color optimization, mitigating artifacts during aggressive structural abstraction; and (3) a VLM-as-a-Judge evaluation framework that assesses artistic authenticity through aesthetic judgment instead of conventional pixel-level metrics, explicitly addressing the subjective nature of artistic stylization.

Problem

• 3D style transfer
• geometric abstraction
• Post-Impressionism
• structure-aware stylization
• artistic expression

Innovation

• flow-guided
• 3D Gaussian Splatting
• structure-aware style transfer
• geometric abstraction
• VLM-as-a-Judge