The study investigates whether the priors learned by visual generative models align with human perceptions of image naturalness. By measuring prediction errors across 25 image and video generators and using paired relational interventions that alter facial configurations or illumination while preserving low-level statistics, the authors find that loss differences replicate human-like sensitivities, including the Thatcher effect and shape-dependent illumination responses. These loss differences correlate strongly with continuous human naturalness judgments (up to r = 0.84 for faces) and remain informative after controlling for feature distances and standard image quality metrics, revealing that human-like naturalness judgments can dissociate from generic violation detection.
By Taiki Fukiage
The study explores how to fine‑tune visual brain encoding models so that their internal representations better match individual human perceptual similarity judgments. Using similarity data from 100 images collected from eight participants in the Natural Scenes Dataset, the authors adapted a generic similarity model (DreamSim) to create personalized perceptual similarity models for each subject. They then fine‑tuned each participant’s baseline encoder with either generic or personalized similarity information, finding that models trained with personalized judgments were most aligned with human perceptual similarity and preserved inter‑subject correlations of those judgments.
By Daniel Chong, Haomiao Chen, Keith W Jamison, Raja Marjieh, Ilia Sucholutsky, Nori Jacoby, Amy Kuceyeski
The study investigates how internal representations of video diffusion models align with human visual cortex responses. It finds that representations used for future video generation in an autoregressive (AR) model better match cortical activity than those for observed video, with future‑generation alignment concentrated in higher‑order visual areas. A behavioral experiment further shows that humans prefer videos enhanced by layers that align more strongly with cortical responses.
By Chang-Bae Bang, Hyungjin Chung, Byung-Hoon Kim
The study analyzes 162 vision models and decomposes their object similarity structures into a few non‑negative dimensions. It distinguishes universal dimensions—those that recur across models—from model‑specific ones, finding that universal dimensions are more interpretable and driven by conceptual image properties. Models with more universal dimensions also better predict macaque IT activity and human similarity judgments, suggesting these representations align with biological vision.
By Florian P. Mahner, Johannes Roth, Ka Chun Lam, Michael F. Bonner, Francisco Pereira, Martin N. Hebart
LLaVA‑Assessor is a unified large multi‑modal model (LMM) designed for visual quality assessment, combining image and video inputs. It introduces a two‑task framework—quality interpretation and quality scoring—supported by an adaptive architecture, a rigorous human‑annotated dataset, and a machine‑synthesized data expansion pipeline. The model employs a prompt‑disentanglement strategy to stabilize multi‑task training and achieves strong performance across 11 quality scoring test sets and 4 interpretation benchmarks.
By Ziheng Jia, Zicheng Zhang, Jiaying Qian, Guangtao Zhai, Xiongkuo Min
arXiv:2609.25716v1 Announce Type: new
Abstract: Reference-based image quality assessment (IQA) metrics aim to reflect how humans perceive the perceptual distance between a pair of images. To learn ho...
By Jaihyun Lew, Mingi Jung, Minjun Park, Wooseok Song, Sungroh Yoon
arXiv:2608.24782v1 Announce Type: new
Abstract: Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Measure (...
By Manish Sharma, Timothy Yim, Clifton Forlines
Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity.
Traditional image similarity metrics such as Mean Squared Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and the Structural Similarity Index Measure (SSIM) rely on pixel-level comparisons and often f...
arXiv:2605.05556v2 Announce Type: replace
Abstract: Artificial neural networks trained on visual tasks develop internal representations resembling those of the primate visual system, a discovery that...
By Yash Mehta, Michael F. Bonner
The paper proposes rethinking image quality assessment (IQA) for embodied tasks by moving from generic score regression to goal‑conditioned judgments based on task utility. It introduces an MLLM‑based IQA agent that reasons about task requirements, grounds quality evidence, and outputs decision‑facing assessments. Experiments on VisDrone show that conventional perceptual metrics and generic IQA scores poorly predict downstream VLM task success, whereas a task‑conditioned utility score better indicates whether visual input supports the target task.
By Jirong Zha, Yanwei Liao, Yemin Wang, Xiangmin Yi, Siqi Peng, Yingfeng Chen, Chen Gao, Xinlei Chen
arXiv:2607. 16214v1 Announce Type: cross Abstract: Image descriptions represented with language models (LMs) predict human brain responses to naturalistic images in high-level visual regions, but the factors driving this predictivity remain unclear.
By Anna Bavaresco, Ina Klari\'c, Raquel Fern\'andez, Marie-Francine Moens