多模态图像着色：量化文本条件引导对灰度到彩色转换的影响
Multimodal Image Colorization: Quantifying the Impact of Text-Conditioned Guidance on Grayscale-to-Color Translation
AI总结：
本文通过U-Net和Stable Diffusion 1.5两种架构，量化了CLIP文本条件对灰度图像着色质量的影响，发现文本条件显著提升了PSNR、SSIM和色彩度，降低了LPIPS。
摘要：
灰度图像常见于历史照片修复、医学成像和艺术媒体。然而，自动为这些图像着色仍然是计算机视觉中的一个重大挑战，因为许多合理的着色可能对应于相同的灰度输入。在这项工作中，我们量化了文本条件对灰度到彩色图像模型的像素级和感知指标的影响。具体来说，我们比较了两种架构，U-Net和Stable Diffusion 1.5，每种架构在有和没有CLIP文本条件的情况下进行测试，同时保持所有其他变量不变。我们的结果表明，在U-Net层级，文本条件使PSNR提高了5.6%，SSIM提高了1.2%，色彩度提高了36.6%，同时LPIPS降低了7.6%。在Stable Diffusion层级，文本条件使PSNR提高了5.8%，SSIM提高了1.5%，色彩度提高了0.6%，同时LPIPS降低了11.3%。这些结果表明，文本条件在两种架构规模上对着色质量提供了一致且可衡量的改进。
英文摘要：
Grayscale images are commonly found in historical photography restoration, medical imaging, and artistic media. However, automatically applying color to these images remains a significant challenge in computer vision because many plausible colorizations can correspond to the same grayscale input. In this work, we quantify the effect of text conditioning on pixel-level and perceptual metrics for grayscale-to-color image models. Specifically, we compare two architectures, a U-Net and Stable Diffusion 1.5, each tested with and without CLIP text conditioning while holding all other variables constant. Our results show that text conditioning improves PSNR by 5.6%, SSIM by 1.2%, and colorfulness by 36.6%, while reducing LPIPS by 7.6% in the U-Net tier. In the Stable Diffusion tier, text conditioning improves PSNR by 5.8%, SSIM by 1.5%, and colorfulness by 0.6%, while reducing LPIPS by 11.3%. These results indicate that text conditioning provides consistent, measurable improvements to colorization quality across both architecture scales.
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。
