发丝守护者：在深度、立体和新视角中拯救软边界
Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views
针对细软边界（如发丝）在深度估计和新视角合成中的模糊问题，提出可插拔的深度修复网络和基于前向变形+生成式修复的视角合成流程，可直接用于提升现有深度模型和NVS方法在边界区域的细节保真度。
原文依据 we first propose a novel data curation pipeline that leverages image matting datasets for training and design a depth fixer network to automatically identify soft boundary regions.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论细软边界（如纤细发丝）在自然和计算机生成图像中普遍存在，但由于前景与背景线索的模糊混合，它们对3D视觉仍具挑战性。本文提出发丝守护者（HairGuard），一个旨在恢复3D视觉任务中细粒度软边界细节的框架。具体而言，我们首先提出一种新颖的数据整理流程，利用图像抠图数据集进行训练，并设计一个深度修复网络来自动识别软边界区域。借助门控残差模块，深度修复网络在软边界周围精确细化深度，同时保持全局深度质量，从而可与最优深度模型即插即用集成。对于视角合成，我们执行基于深度的前向变形以保留高保真纹理，随后使用生成式场景绘制器填充去遮挡区域并消除软边界内多余的背景伪影。最后，颜色融合器自适应地组合变形和修复结果，以生成具有一致几何和细粒度细节的新视角。大量实验表明，HairGuard在单目深度估计、立体图像/视频转换和新视角合成方面均达到最优性能，并在软边界区域取得显著改进。
英文原文摘要 1360 字符
Soft boundaries, like thin hairs, are commonly observed in natural and computer-generated imagery, but they remain challenging for 3D vision due to the ambiguous mixing of foreground and background cues. This paper introduces Guardians of the Hair (HairGuard), a framework designed to recover fine-grained soft boundary details in 3D vision tasks. Specifically, we first propose a novel data curation pipeline that leverages image matting datasets for training and design a depth fixer network to automatically identify soft boundary regions. With a gated residual module, the depth fixer refines depth precisely around soft boundaries while maintaining global depth quality, allowing plug-and-play integration with state-of-the-art depth models. For view synthesis, we perform depth-based forward warping to retain high-fidelity textures, followed by a generative scene painter that fills disoccluded regions and eliminates redundant background artifacts within soft boundaries. Finally, a color fuser adaptively combines warped and inpainted results to produce novel views with consistent geometry and fine-grained details. Extensive experiments demonstrate that HairGuard achieves state-of-the-art performance across monocular depth estimation, stereo image/video conversion, and novel view synthesis, with significant improvements in soft boundary regions.