EmoScene: A Dual-space Dataset for Controllable Affective Image Generation

TL;DR

EmoScene introduces a large-scale dataset combining affective and perceptual scene attributes to improve controllability in affective image generation using diffusion models.

Contribution

The paper presents EmoScene, a dual-space emotion dataset with annotations for affective and perceptual factors, and benchmarks affect control in diffusion-based image synthesis.

Findings

Discrete emotions map systematically within the VAD space.

Affect correlates with perceptual scene attributes.

Baseline model demonstrates controllability via dual-space supervision.

Abstract

Text-to-image diffusion models have achieved high visual fidelity, yet precise control over scene semantics and fine-grained affective tone remains challenging. Human visual affect arises from the rapid integration of contextual meaning, including valence, arousal, and dominance, with perceptual cues such as color harmony, luminance contrast, texture variation, curvature, and spatial layout. However, current text-to-image models rarely represent affective and perceptual factors within a unified representation, which limits their ability to synthesize scenes with coherent and nuanced emotional intent. To address this gap, we construct EmoScene, a large-scale dual-space emotion dataset that jointly encodes affective dimensions and perceptual attributes, with contextual semantics provided as supporting annotations. EmoScene contains 1.2M images across more than three hundred real-world scene categories, each annotated with discrete emotion labels, continuous VAD values, perceptual descriptors and textual captions. Multi-space analyses reveal how discrete emotions occupy the VAD space and how affect systematically correlates with scene-level perceptual factors. To benchmark EmoScene, we provide a lightweight reference baseline that injects dual-space controls into a frozen diffusion backbone via shallow cross-attention modulation, serving as a reproducible probe of affect controllability enabled by dual-space supervision.