mlsanityData to 7 Oct 2026

LLDif: Diffusion Models for Low-light Emotion Recognition

arXiv 2408.04235 ↗First posted 8 Aug 2024cs.CVcited by 0

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 21 of its 29 references that are in the map. First posted on arXiv 8 Aug 2024.

Builds on

21 of 29 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024LRDif: Diffusion Models for Under-Display Camera Emotion Recognition1 Feb

Other references · 20

  1. 2022Paint by Example: Exemplar-based Image Editing with Diffusion Modelscited by 489
  2. 2022SINE: SINgle Image Editing with Text-to-Image Diffusion Modelscited by 159
  3. 2016Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distributioncited by 158
  4. 2020Suppressing Uncertainties for Large-Scale Facial Expression Recognitioncited by 157
  5. 2023MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformercited by 124
  6. 2022CARD: Classification and Regression Diffusion Modelscited by 102
  7. 2023Ambiguous Medical Image Segmentation using Diffusion Modelscited by 92
  8. 2021Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognitioncited by 89
  9. 2022Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognitioncited by 67
  10. 2021Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognitioncited by 55
  11. 2023ResDiff: Combining CNN and Diffusion Model for Image Super-Resolutioncited by 53
  12. 2019Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Datasetcited by 39
8 more
  1. 2019Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Softwarecited by 34
  2. 2021Expression Snippet Transformer for Robust Video-based Facial Expression Recognitioncited by 33
  3. 2023POSTER++: A simpler and stronger facial expression recognition networkcited by 25
  4. 2023HTNet for micro-expression recognitioncited by 20
  5. 2021Learning to Amend Facial Expression Representation via De-albino and Affinitycited by 19
  6. 2022Transformer-Based Self-Supervised Learning for Emotion Recognitioncited by 16
  7. 2023Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognitioncited by 13
  8. 2024Authentic Emotion Mapping: Benchmarking Facial Expressions in Real Newscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Emotion Diffusion Classifier with Adaptive Margin Discrepancy Training for Facial Expression Recognition
  2. 2024EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning
  3. 2025Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition
  4. 2026Multimodal Emotion Recognition via Causal-Diffusion Bridge (Affect-Diff)
  5. 2023LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
  6. 2023EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition
  7. 2025Evaluating Open-Source Vision Language Models for Facial Emotion Recognition against Traditional Deep Learning Models
  8. 2024Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer