The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Beauty assessments from Multimodal Large Language Models (MLLMs) are increasingly popular, prompting a study comparing 2,513 human ratings to four commercial AI models—Claude, Gemini, GPT, and Grok. The study found that MLLMs consistently rate faces more favorably and with a narrower range than humans, yet they maintain strong correlations with human judgments and accurately track the rank‑ordering of faces. While all models agree strongly with each other, Grok showed the lowest agreement with human ratings, and only face age emerged as a common predictor of attractiveness across humans and MLLMs.
This paper introduces a Conditional Variational Autoencoder (CVAEs) approach that generates realistic, controllable emotional facial expressions for virtual humans. Trained on a small dataset of 7,680 samples covering six basic emotions at low and high intensity, the model learns latent representations that preserve key expressive characteristics across intensity levels. The method enables animators to produce emotionally expressive virtual characters without actor performances or manual artistic effort.
The paper introduces a multidimensional observer model that represents images as distributions in a latent perceptual space and models human image quality judgment as comparisons of noisy samples. By aligning the model with neural representations in the primate ventral stream and fitting it to large-scale behavioral data, the authors demonstrate that the perceptual space required for human quality assessment is extremely low-dimensional relative to the image space. The study reveals that the structure of this perceptual space differs between low-level and high-level quality judgments, indicating that humans construct task-dependent perceptual spaces during visual decision making.
arXiv:2608.31053v1 Announce Type: new Abstract: Diffusion models have achieved strong results in high-fidelity image synthesis, but their iterative sampling process makes large-scale generation compu...
Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained facial edits.
The paper introduces Semantic Boundary Predictor (SBP), an inference‑time framework that improves demographic fairness in synthetic face generation by applying a single, one‑shot intervention during reverse denoising. SBP learns linear semantic boundaries from late‑stage latent representations and applies them only at the initial noisy latent, leaving the rest of the diffusion process unchanged. Experiments on CelebA‑HQ show significant reductions in fairness disparity—98% for gender, 95% for binary race, and 15% for four‑class race—while preserving image quality across demographic groups.