发表机构
University of California, Davis（加州大学戴维斯分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出RDGSplat框架，从冻结的3D基础模型解码渲染专用几何，通过复制解码器并仅用光度监督优化，引入目标姿态条件适配器，在多个基准上提升新视角合成性能，同时保持度量预测不变。
AI 中文摘要
3D基础模型通过在其用于重建的表示上携带高斯头，能够实现高效的新视角合成。然而，它们渲染的视角质量不及它们恢复的几何质量，因为该几何是在度量目标下估计的，且从未根据其渲染效果进行评分。近期方法通过更新骨干网络权重来缓解这一问题，但它们因此丢弃了模型所构建的度量预测，并且必须针对每个新的骨干网络重复此过程。为此，我们提出了RDGSplat，一个从冻结的3D基础模型中解码出第二个专用于渲染的几何的框架，同时保持其度量预测不变。具体而言，我们设计了渲染专用几何解码（Render-Dedicated Geometry Decoding），该方法复制预训练的解码器，并仅通过光度监督来优化这些副本。然后，引入目标姿态条件适配器（Target-Pose Conditioned Adapter），以根据目标相机姿态而非目标图像来重新表述这些解码器读取的表示。大量实验表明，RDGSplat在四个基准测试上提升了三个前馈骨干网络的新视角合成性能，且所有预训练权重均被冻结。在RE10K上，它将WM2.0从20.918 dB提升至24.266 dB，同时针对冻结的1.4B骨干网络训练了205.5M新增参数，且同一模型预测的深度和姿态保持不变。
英文摘要
3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. However, the views they render fall short of the geometry they recover, because that geometry is estimated under a metric objective and never scored on how it renders. Recent methods alleviate this by updating the backbone weights, but they thereby discard the metric predictions the model was built for and must be repeated for every new backbone. To this end, we propose RDGSplat, a framework that decodes a second geometry dedicated to rendering from a frozen 3D foundation model, leaving its metric predictions intact. In particular, we devise Render-Dedicated Geometry Decoding, which duplicates the pretrained decoders and optimizes the duplicates under photometric supervision alone. Then, a Target-Pose Conditioned Adapter is introduced to reformulate the representation those decoders read, conditioned on the target camera pose rather than the target image. Extensive experiments show that RDGSplat improves novel view synthesis across three feed-forward backbones on four benchmarks, with every pretrained weight frozen. On RE10K, it raises WM2.0 from 20.918 to 24.266\,dB while training 205.5\,M added parameters against a frozen 1.4\,B backbone, and the depth and pose the same model predicts are unchanged.
