3dgs-sc：面向3D高斯泼溅的可控静态屏幕内容基准
3dgs-sc: a controlled static screen-content benchmark for 3d gaussian splatting
AI总结：
针对3DGS中高图像保真度与屏幕内容可读性不匹配的问题，提出受控静态屏幕内容基准3DGS-SC，通过十场景和五方法比较，揭示仅凭保真度评估会导致方法选择失败。
AI中文摘要：
高图像保真度是否意味着3D高斯泼溅（3DGS）中可读的屏幕内容？我们引入了3DGS-SC，一个用于检验这一不匹配问题的受控静态屏幕内容数据集和基准。十个程序化场景提供了固定的多视角分割、精确相机、屏幕掩码、文本框和转录文本。该协议将整体图像保真度、屏幕区域保真度、OCR可读性和边缘保留分开评估。在报告的五方法比较中，LightGaussian在屏幕PSNR上仅比Mip-Splatting高0.08 dB，但在OCR准确率上却落后12.7个百分点。在所有十对方法中，屏幕PSNR和OCR排序在七种情况下不一致。这些汇总结果暴露了仅基于保真度评估的方法选择失败。作为对先前文本感知3DGS研究的补充，3DGS-SC针对受控显示器接口和精确标注；场景级鲁棒性和采集效应仍是待验证的开放问题。
英文摘要：
Does high image fidelity imply readable screen content in 3D Gaussian Splatting (3DGS)? We introduce 3DGS-SC, a controlled static screen-content dataset and benchmark for examining this mismatch. Ten procedural scenes provide fixed multi-view splits, exact cameras, screen masks, text boxes, and transcripts. The protocol separates whole-image fidelity, screen-region fidelity, OCR readability, and edge preservation. In the reported five-method comparison, LightGaussian exceeds Mip-Splatting in screen PSNR by only 0.08 dB, yet trails it in OCR accuracy by 12.7 percentage points. Across all ten method pairs, screen-PSNR and OCR orderings disagree in seven cases. These aggregate results expose a method-selection failure of fidelity-only evaluation. Complementing prior text-aware 3DGS research, 3DGS-SC targets controlled monitor interfaces and exact annotations; scene-wise robustness and acquisition effects remain open validation questions.
