EmoSpace: Fine-Grained Emotion Prototype Learning for Immersive Affective Content Generation

2026-02-12

AI Summary

Existing generative methods struggle to model fine-grained emotional semantics, limiting affective expression in immersive VR content. This work proposes an unsupervised emotion-aware generation framework that operates without explicit emotion labels. By leveraging vision–language alignment, the model learns dynamic and interpretable hierarchical emotion prototypes. Fine-grained emotional control is achieved through multi-prototype guidance, temporal emotion fusion, and attention reweighting mechanisms. The approach significantly outperforms current methods across tasks including emotion-conditioned image outpainting, stylized generation, and VR panoramic synthesis. Furthermore, user studies reveal a unique amplification effect of VR environments on emotional perception, underscoring the framework’s effectiveness in immersive settings.

Technology Category

• Computer Vision: Language and Vision
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Emotion is important for creating compelling virtual reality (VR) content. Although some generative methods have been applied to lower the barrier to creating emotionally rich content, they fail to capture the nuanced emotional semantics and the fine-grained control essential for immersive experiences. To address these limitations, we introduce EmoSpace, a novel framework for emotion-aware content generation that learns dynamic, interpretable emotion prototypes through vision-language alignment. We employ a hierarchical emotion representation with rich learnable prototypes that evolve during training, enabling fine-grained emotional control without requiring explicit emotion labels. We develop a controllable generation pipeline featuring multi-prototype guidance, temporal blending, and attention reweighting that supports diverse applications, including emotional image outpainting, stylized generation, and emotional panorama generation for VR environments. Our experiments demonstrate the superior performance of EmoSpace over existing methods in both qualitative and quantitative evaluations. Additionally, we present a comprehensive user study investigating how VR environments affect emotional perception compared to desktop settings. Our work facilitates immersive visual content generation with fine-grained emotion control and supports applications like therapy, education, storytelling, artistic creation, and cultural preservation. Code and models will be made publicly available.

Problem

• emotion
• virtual reality
• fine-grained control
• affective content generation
• immersive experience

Innovation

• emotion prototype learning
• vision-language alignment
• fine-grained emotional control
• controllable generation
• immersive VR content