AI 中文总结
针对混合质量JPEG图像损坏3D高斯溅射（3DGS）跨视图高斯更新的问题，提出JSGS方法，利用JPEG量化表构建观测算子并结合块差异正则化，在7个场景和3种设置下获最优指标且渲染速度约150 FPS。
AI 中文摘要
标准3D高斯溅射（3DGS）假设每个输入图像都能忠实地采样场景辐射度，但混合质量的JPEG图像会违反该假设，因为压缩导致的块效应和振铃伪影会损坏跨视图共享高斯的更新。为解决此问题，我们提出了JSGS——基于混合质量视图的3D高斯溅射的JPEG状态引导监督。JSGS利用每个JPEG文件中存储的亮度和色度量化表，构建特定于视图的JPEG观测算子，该算子对每个渲染视图进行编码和解码，以与对应的解码输入图像进行域匹配比较。亮度量化表在固定的中间频带内提供连续权重，低频带的损失锚定粗结构，而加权中间频带损失在选定的DCT坐标间重新分配监督，产生的块差异还会引导高斯控制器对差异区域中不透明度高的小基元进行正则化。在7个场景和3种混合质量设置下，JSGS在每种设置下均实现了最低的平均LPIPS和最高的平均SSIM，同时以约150 FPS的速度渲染。代码：this https URL。
英文摘要
Standard 3D Gaussian Splatting (3DGS) assumes that every input image faithfully samples scene radiance. However, mixed-quality JPEG images violate this assumption because compression-induced blocking and ringing artifacts can corrupt updates to Gaussians shared across views. To address this problem, we propose JPEG State-Guided Supervision for 3D Gaussian Splatting from Mixed-Quality Views (JSGS). JSGS uses luminance and chrominance quantization tables stored in each JPEG file to construct a view-specific JPEG observation operator. This operator encodes and decodes each rendered view for domain-matched comparison with the corresponding decoded input image. The luminance quantization table supplies continuous weights within a fixed middle frequency band. A loss in the low frequency band anchors coarse structure, while the weighted middle frequency loss redistributes supervision among the selected DCT coordinates. The resulting block disagreement also guides the Gaussian Controller to regularize small primitives with high opacity in disagreement regions. Across seven scenes and three mixed-quality schedules, JSGS achieves the lowest mean LPIPS and the highest mean SSIM under every schedule while rendering at approximately 150 FPS. Code: https://github.com/Jayden-Cui/JSGS.
