arXiv AI
Jul 16
Beyond Color Geometry: Evaluating Human-Like Color Representations in Vision Models
arXiv:2607. 13647v1 Announce Type: cross Abstract: Do vision models see colors the way humans do?
Perceptual Color Difference Modeling Using Machine Learning and Human Similarity Judgments
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.
Related stories
arXiv Computer Vision
Sep 15
MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images
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 AI
Aug 17
Seeing Red, Thinking Bad: Color Bias in Vision Language Models
arXiv:2608. 14286v1 Announce Type: cross Abstract: Vision language models (VLMs) are increasingly used in industrial decision-making systems, such as recruitment support and recommendation.
arXiv AI
Sep 10
Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs
arXiv:2609.09124v1 Announce Type: cross Abstract: Visual encoders construct a representation of the image input for Vision-Language models. How much conceptual, as opposed to immediately visible, inf...
arXiv AI
Sep 18
Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Paint-Anything introduces a unified hex-prompt interface that allows users to specify any 24‑bit hex color for both image generation and editing. The method trains on a new Paint‑500K dataset created from real images with object grounding, perceptual color labeling, and editing‑pair synthesis, and supplements this with pure‑color anchors to address shadow‑induced color inaccuracies. Evaluated on the newly proposed Any Color Benchmark (ACBench), Paint‑Anything achieves significant improvements over the base FLUX.2‑4B model, boosting T2I and editing scores by 85.3 % and 28.3 % respectively, and outperforms competing methods on the CompColor metric.
Hugging Face Trending Papers
Sep 8
Canonical Color as a Lens into Concept Decodability in Vision Encoders and VLMs
The paper investigates how vision encoders and Vision‑Language Models (VLMs) encode conceptual information by using canonical color as a test case. By creating a dataset of objects with canonical colors and probing encoders with both color and grayscale images, the authors show that canonical color can still be decoded from grayscale inputs and is linked to predicted object identity. They further demonstrate that post‑training of VLMs can significantly influence color decodability within the vision encoder, suggesting that canonical color is a useful tool for tracing conceptual semantics in these models.
arXiv AI
Aug 20
When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't
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.
arXiv Machine Learning
Aug 12
More Accurate, Less Human: Gestalt Grouping in Vision Models
arXiv:2608. 10195v1 Announce Type: cross Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects.
arXiv Computer Vision
Aug 24
What Color Is the Text? A Benchmark for Hallucination Induced by Image-Embedded Prompt
The paper introduces Embedded Stroop, a diagnostic test that embeds text prompts directly into images to study interference in multimodal large language models (MLLMs). Using the What-Color-Is-the-Text (WCIT) benchmark, which tests 59 fine‑grained colors in standard, flipped, and masked conditions, the authors evaluate 16 models and find that while exact color accuracy is low (6.3%), models still recognize coarse color families (38.4%) but frequently hallucinate the embedded word instead of the true color (Stroop Hallucination Rate of 21.6%). Masking or flipping the embedded text reduces hallucinations, indicating that semantic legibility can dominate visual color perception in MLLMs.
arXiv Machine Learning
Aug 20
Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching
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.
arXiv Computer Vision
Sep 17
Visual Autoregressive Priors for RAW-to-sRGB Image Signal Processing
arXiv:2609.18302v1 Announce Type: new Abstract: RAW-to-sRGB image signal processing (ISP) must recover perceptually faithful colors and fine details from sensor measurements, often under imperfect sp...
arXiv Computer Vision
Aug 26
Image Difference Quantification Using Autoencoder-Based Latent Representations
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 (...