The Flow has not summarised this story yet — read it at arXiv Computer Vision.
The paper presents a data‑driven method for estimating perceptual color differences by training regression models on human similarity judgments of 2,000 color pairs. Using COLIBRI fuzzy linguistic categories as features, linear regression achieves an R² of 0.595, outperforming RGB and HSI representations. The best result, an R² of 0.703, is obtained with LightGBM on a combined representation, showing that graded perceptual categories improve color‑difference prediction.
arXiv:2609.14495v1 Announce Type: new Abstract: Image colorization is an inherently ill-posed task, since a single grayscale image may correspond to multiple plausible colorized results. Consequently...
arXiv:2607. 13647v1 Announce Type: cross Abstract: Do vision models see colors the way humans do?
EventSeeColor is a method that reconstructs color images from monochrome event camera data. It combines event‑reconstructed grayscale images with aligned events to guide a diffusion colorizer, using semantic context and region‑balanced chroma supervision to improve color fidelity. Evaluations on two real event datasets show that EventSeeColor outperforms existing methods in structural similarity, perceptual scores, and chromatic‑region color difference.
The paper introduces Colorist, a data‑augmentation method that uses classical statistical color matching to generate domain‑shifted medical images. By applying global mean‑standard‑deviation matching in RGB space, Colorist creates structurally intact variations without neural networks, outperforming deep generative models in fidelity and color alignment. Across multiple medical imaging datasets, it boosts balanced accuracy by up to 9% over state‑of‑the‑art domain‑generalization regularizers and 13% over no augmentation, while reducing computational cost and preserving anatomical structure.
The paper introduces the Graded Color Attribution (GCA) dataset, a benchmark that tests whether Vision‑Language Models (VLMs) and humans can articulate and follow a threshold rule for labeling objects by color. In experiments, humans consistently adhere to their stated rules, while VLMs—despite accurately estimating color coverage—often violate their own introspective rules, especially when world‑knowledge priors are present. This discrepancy highlights a miscalibration in VLM self‑knowledge that differs from human cognition.