发表机构
KAIST; Google; Microsoft; ETH Zürich（韩国科学技术院; 谷歌公司; 微软公司; 苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GenRec 是一种多视图流匹配模型，通过架构等内置重建与生成划分，在 RealEstate10K 等数据集的单视图外推、两视图插值任务中，兼顾观测区域高重建保真度与未观测区域优感知质量。
AI 中文摘要
从稀疏输入图像生成新视角视图的任务中，生成过程极少是完全重建或完全生成的：在某些源视图中可见的像素具有唯一的正确值，仅受视图相关着色的调制；而在非遮挡区域或超出捕获体积的像素则存在多种合理补全的分布。现有的生成式新视角合成方法将这些不同 regime（区域）统一在单一的均匀损失下，即使通过变形点云或投影深度注入场景几何，也模糊了几何保真度与创造性幻觉之间的界限。我们提出 GenRec，一种多视图流匹配模型，其架构、监督和梯度流中直接内置了重建-生成的划分。在源自源相机和单目深度估计器的观测掩码引导下，流匹配主干网络联合对所有目标视图的 RGB 和场景坐标图进行去噪，同时像素空间细化阶段在观测像素上恢复高频细节；同一掩码控制监督，使回归信号不会污染生成先验。在 RealEstate10K、DL3DV-10K 和 Mip-NeRF 360 数据集上，无论是单视图外推还是两视图插值，GenRec 在观测区域均达到最佳重建保真度，且在未观测区域的感知质量上也超越了纯生成基线，证明了我们方法的有效性。
英文摘要
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated only by view-dependent shading, while pixels in disocclusions or beyond the captured volume admit a distribution of plausible completions. Existing generative novel-view-synthesis methods conflate these regimes under a single uniform loss, blurring the line between geometric fidelity and creative hallucinations even when scene geometry is injected through warped point clouds or projected depth. We introduce GenRec, a multi-view flow matching model that builds the reconstruction--generation split directly into its architecture, supervision, and gradient flow. Guided by an observation mask derived from the source cameras and a monocular depth estimator, a flow matching backbone jointly denoises RGB and scene-coordinate maps across all target views, while a pixel-space refinement stage restores high-frequency detail on observed pixels; the same mask gates supervision so regression signals do not contaminate the generative prior. Across RealEstate10K, DL3DV-10K, and Mip-NeRF~360, in both single-view extrapolation and two-view interpolation, GenRec attains the best reconstruction fidelity in observed regions while also surpassing purely generative baselines on perceptual quality in unobserved ones, showing the effectiveness of our approach.
