Style-Aware Gloss Control for Generative Non-Photorealistic Rendering

2026-02-18

AI Summary

This work addresses the challenge in non-photorealistic rendering where glossiness and artistic style are difficult to control independently. By constructing a dataset of stylized objects with systematically varied gloss and style attributes, the authors train an unsupervised generative model that, for the first time, achieves hierarchical disentanglement of gloss and style in the latent space. They further introduce a lightweight adapter module that efficiently integrates this disentangled representation into latent diffusion models, enabling fine-grained and independent manipulation of both glossiness and artistic style in generated images. Compared to existing approaches, the proposed method significantly enhances generation controllability while preserving visual fidelity.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Humans can infer material characteristics of objects from their visual appearance, and this ability extends to artistic depictions, where similar perceptual strategies guide the interpretation of paintings or drawings. Among the factors that define material appearance, gloss, along with color, is widely regarded as one of the most important, and recent studies indicate that humans can perceive gloss independently of the artistic style used to depict an object. To investigate how gloss and artistic style are represented in learned models, we train an unsupervised generative model on a newly curated dataset of painterly objects designed to systematically vary such factors. Our analysis reveals a hierarchical latent space in which gloss is disentangled from other appearance factors, allowing for a detailed study of how gloss is represented and varies across artistic styles. Building on this representation, we introduce a lightweight adapter that connects our style- and gloss-aware latent space to a latent-diffusion model, enabling the synthesis of non-photorealistic images with fine-grained control of these factors. We compare our approach with previous models and observe improved disentanglement and controllability of the learned factors.

Problem

• gloss control
• non-photorealistic rendering
• artistic style
• material appearance
• disentanglement

Innovation

• gloss control
• non-photorealistic rendering
• disentangled representation
• latent diffusion model
• style-aware generation