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

arXiv: https://arxiv.org/abs/2604.00933 · HTML: https://mlsanity.com/paper/2604.00933/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 38 of its 52 references that are in the map.
- First posted on arXiv 1 Apr 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 30 of 38)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [ArtEmis: Affective Language for Visual Art](https://mlsanity.com/paper/2101.07396/) (2021)
- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark](https://mlsanity.com/paper/1605.02677/) (2016)
- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances](https://mlsanity.com/paper/2203.06935/) (2022)
- [GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition](https://mlsanity.com/paper/2312.04293/) (2023)
- [EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2401.04608/) (2024)
- [EmoEdit: Evoking Emotions through Image Manipulation](https://mlsanity.com/paper/2405.12661/) (2024)
- [MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition](https://mlsanity.com/paper/2401.03429/) (2024)
- [EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model](https://mlsanity.com/paper/2501.05710/) (2025)
- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [Emotion Recognition from Multiple Modalities: Fundamentals and Methodologies](https://mlsanity.com/paper/2108.10152/) (2021)
- [FindingEmo: An Image Dataset for Emotion Recognition in the Wild](https://mlsanity.com/paper/2402.01355/) (2024)
- [A Survey on Facial Expression Recognition of Static and Dynamic Emotions](https://mlsanity.com/paper/2408.15777/) (2024)
- [JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups](https://mlsanity.com/paper/2404.04458/) (2024)
- [Affective Image Editing: Shaping Emotional Factors via Text Descriptions](https://mlsanity.com/paper/2505.18699/) (2025)
- [A Unified and Interpretable Emotion Representation and Expression Generation](https://mlsanity.com/paper/2404.01243/) (2024)
- [AffectGAN: Affect-Based Generative Art Driven by Semantics](https://mlsanity.com/paper/2109.14845/) (2021)
- [CoEmoGen: Towards Semantically-Coherent and Scalable Emotional Image Content Generation](https://mlsanity.com/paper/2508.03535/) (2025)
- [Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification](https://mlsanity.com/paper/2503.09962/) (2025)
- [A Comprehensive Survey on Affective Computing; Challenges, Trends, Applications, and Future Directions](https://mlsanity.com/paper/2305.07665/) (2023)
- [A Review of Human Emotion Synthesis Based on Generative Technology](https://mlsanity.com/paper/2412.07116/) (2024)

## Built on by (most cited first, 1 of 1)

- [What Can I Edit? Open-Ended Strategy Discovery and the Emotion Editability Landscape](https://mlsanity.com/paper/2607.23920/) (2026)

## Abstract (arXiv)

Text-to-image diffusion models achieve high visual fidelity, yet fine-grained affective control remains difficult because textual emotion cues often fail to specify the visual perceptual factors underlying affective expression. Existing visual-affect datasets are likewise often limited to discrete labels, specific domains, or limited supervision of perceptual attributes. We introduce EmoScene, a large-scale dual-space dataset for controllable affective image generation, containing 1.2M images across more than 300 scene categories. Its affective space jointly represents discrete emotions and continuous valence--arousal--dominance (VAD), its perceptual space records measurable appearance attributes, and contextual descriptions ground both in scene semantics. EmoScene combines multi-model annotation with human-in-the-loop quality control. A random audit of 30,519 images yields 91.22% agreement on discrete emotion labels, while an independent multi-rater evaluation yields Fleiss' kappa=0.85. After controlling for source and scene composition, affective dimensions and perceptual attributes exhibit stable associations across data sources, reflecting statistical tendencies rather than deterministic visual rules. To demonstrate the dataset's utility, we further develop AffectCtrl, which learns residuals in the conditioning space of frozen diffusion models to support categorical emotion generation and continuous control over VAD, brightness, and saturation. AffectCtrl achieves 85.75% categorical emotion accuracy, outperforms EmotiCrafter in valence and arousal control under a shared evaluation protocol, and obtains Pearson correlations of 0.673--0.765 across all five continuous axes. These results demonstrate that EmoScene provides a scalable data foundation for analyzing and controlling affective expression in visual generation.