ChromouVQA：在色度伪装图像下评估视觉-语言模型的基准测试
ChromouVQA: Benchmarking Vision-Language Models under Chromatic Camouflaged Images
AI总结：
ChromouVQA通过色度伪装图像评估视觉-语言模型在复杂背景下的表现，提出对比度配方提升形状恢复能力。
摘要：
视觉-语言模型（VLMs）在多模态理解方面已取得进展，但在目标嵌入在杂乱背景中需要图底分离时仍面临挑战。为此，我们引入了ChromouVQA，一个基于Ishihara风格色度伪装图像的大型多任务基准测试。我们扩展了经典的点板，采用多种填充几何形状，并变化色度分离、密度、大小、遮挡和旋转，记录完整的元数据以确保可重复性。该基准测试涵盖九个视觉-问题-回答任务，包括识别、计数、比较和空间推理。对人类和VLMs的评估揭示了显著的差距，尤其是在微妙的色度对比或干扰的几何填充下。我们还提出了一种模型无关的对比度配方，将轮廓与其伪装渲染对齐，提高了全局形状的恢复能力。ChromouVQA提供了一个紧凑、受控的基准测试，用于可重复的评估和扩展。代码和数据集可在https://github.com/Chromou-VQA-Benchmark/Chromou-VQA获取。
英文摘要：
Vision-Language Models (VLMs) have advanced multimodal understanding, yet still struggle when targets are embedded in cluttered backgrounds requiring figure-ground segregation. To address this, we introduce ChromouVQA, a large-scale, multi-task benchmark based on Ishihara-style chromatic camouflaged images. We extend classic dot plates with multiple fill geometries and vary chromatic separation, density, size, occlusion, and rotation, recording full metadata for reproducibility. The benchmark covers nine vision-question-answering tasks, including recognition, counting, comparison, and spatial reasoning. Evaluations of humans and VLMs reveal large gaps, especially under subtle chromatic contrast or disruptive geometric fills. We also propose a model-agnostic contrastive recipe aligning silhouettes with their camouflaged renderings, improving recovery of global shapes. ChromouVQA provides a compact, controlled benchmark for reproducible evaluation and extension. Code and dataset are available at https://github.com/Chromou-VQA-Benchmark/Chromou-VQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
