XPaintNet：一种无需图像修复网络的极轻量级立体转换框架
XPaintNet: An eXtreme Lightweight Framework for Stereoscopic Conversion without Inpainting Network
提出 Bi-Warp 双向光流与可学习掩码融合的轻量级立体视图合成方法，可复用于需要实时新视图生成且避免图像修复网络的重建或渲染任务。
原文依据 we propose Bi-Warp, a simple yet effective approach that synthesizes the right view without inpainting network by leveraging warping operations.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论随着立体 3D 设备的快速增长，实时立体转换变得日益重要。然而，大多数现有方法依赖于深度估计、前向变换和沉重的图像修复网络，导致高计算成本以及遮挡边界附近的伪影。基于扩散的模型也已被探索，但它们受限于迭代采样和几何不一致性，使其不适合实时部署。为了解决这些问题，我们提出了 Bi-Warp，一种简单而有效的方法，通过利用变换操作合成右视图而无需图像修复网络。我们的方法估计后向光流，近似对应的前向光流，并通过双向变换生成两个候选右视图。一个可学习的掩码自适应地融合候选视图，保持左右几何一致性。基于 Bi-Warp，我们引入了 XPaintNet，一个轻量级网络，在保持 2K 分辨率下超过 100 FPS 的实时性能的同时，达到与最优方法相当的视觉质量。
英文原文摘要 1088 字符
With the rapid growth of stereoscopic 3D devices, real-time stereoscopic conversion has become increasingly essential. However, most existing approach rely on depth estimation, forward warping, and heavy inpainting network, resulting in high computational cost and artifacts near occlusion boundaries. Diffusion-based models have also been explored, but they suffer from iterative sampling and geometric inconsistency, making them unsuitable for real-time deployment. To address these issues, we propose Bi-Warp, a simple yet effective approach that synthesizes the right view without inpainting network by leveraging warping operations. Our approach estimates backward flow, approximates the corresponding forward flow, and generates two candidate right views via bidirectional warping. A learnable mask adaptively fuses the candidates, preserving left-right geometric consistency. Building on Bi-Warp, we introduce XPaintNet, a lightweight network that achieves comparable visual quality to state-of-the-art methods while maintaining real-time performance over 100 FPS at 2K resolution.