LRDif: Diffusion Models for Under-Display Camera Emotion Recognition
Abstract: This study introduces LRDif, a novel diffusion-based framework designed specifically for facial expression recognition (FER) within the context of under-display cameras (UDC). To address the inherent challenges posed by UDC's image degradation, such as reduced sharpness and increased noise, LRDif employs a two-stage training strategy that integrates a condensed preliminary extraction network (FPEN) and an agile transformer network (UDCformer) to effectively identify emotion labels from UDC images. By harnessing the robust distribution mapping capabilities of Diffusion Models (DMs) and the spatial dependency modeling strength of transformers, LRDif effectively overcomes the obstacles of noise and distortion inherent in UDC environments. Comprehensive experiments on standard FER datasets including RAF-DB, KDEF, and FERPlus, LRDif demonstrate state-of-the-art performance, underscoring its potential in advancing FER applications. This work not only addresses a significant gap in the literature by tackling the UDC challenge in FER but also sets a new benchmark for future research in the field.
- “Learning to amend facial expression representation via de-albino and affinity,” arXiv preprint arXiv:2103.10189, 2021.
- “Dive into ambiguity: Latent distribution mining and pairwise uncertainty estimation for facial expression recognition,” in CVPR, 2021.
- “Learning deep global multi-scale and local attention features for facial expression recognition in the wild,” IEEE TIP, 2021.
- “Facial expression recognition based on deep evolutional spatial-temporal networks,” IEEE TIP, 2017.
- “Four-player groupgan for weak expression recognition via latent expression magnification,” KBS, 2022.
- “Htnet for micro-expression recognition,” arXiv preprint arXiv:2307.14637, 2023.
- “Facial smile detection based on deep learning features,” in ACPR, 2015.
- “Relative uncertainty learning for facial expression recognition,” NeurIPS, 2021.
- “Learn from all: Erasing attention consistency for noisy label facial expression recognition,” in ECCV, 2022.
- “Suppressing uncertainties for large-scale facial expression recognition,” in CVPR, 2020.
- “Sd-mtcnn: Self-distilled multi-task cnn.,” in BMVC, 2020.
- “Shallow optical flow three-stream cnn for macro-and micro-expression spotting from long videos,” in ICIP. IEEE, 2021.
- “Poster v2: A simpler and stronger facial expression recognition network,” arXiv preprint arXiv:2301.12149, 2023.
- “Light attention embedding for facial expression recognition,” IEEE TCSVT, 2021.
- “Multi-relations aware network for in-the-wild facial expression recognition,” IEEE TCSVT, 2023.
- “Paint by example: Exemplar-based image editing with diffusion models,” in CVPR, 2023.
- “Lldiffusion: Learning degradation representations in diffusion models for low-light image enhancement,” arXiv preprint arXiv:2307.14659, 2023.
- “Towards real-world blind face restoration with generative diffusion prior,” arXiv preprint arXiv:2312.15736, 2023.
- “Styleswin: Transformer-based gan for high-resolution image generation,” in CVPR, 2022.
- “High-resolution image synthesis with latent diffusion models,” in CVPR, 2022.
- “Diffusiondet: Diffusion model for object detection,” in CVPR, 2023.
- “Learning transferable visual models from natural language supervision,” in ICML, 2021.
- “Facial expression recognition in the wild via deep attentive center loss,” in WACV, 2021.
- “Distract your attention: Multi-head cross attention network for facial expression recognition,” Biomimetics, 2023.
- “Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild,” in CVPR, 2017.
- “Training deep networks for facial expression recognition with crowd-sourced label distribution,” in ICMI, 2016.
- “Latent-ofer: Detect, mask, and reconstruct with latent vectors for occluded facial expression recognition,” in CVPR, 2023.
- “Modular degradation simulation and restoration for under-display camera,” in ACCV, 2022.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.