InfiniDepth：基于神经隐式场的任意分辨率与细粒度深度估计
InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
把深度表示为神经隐式场、用局部隐式解码器在连续 2D 坐标上查询，可让任意分辨率的深度输出与细节恢复摆脱离散网格限制；这一表示可直接用于大视角变化下的新视角合成，减少空洞与伪影。
原文依据 Through a simple yet effective local implicit decoder, we can query depth at continuous 2D coordinates
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有深度估计方法从根本上受限于在离散图像网格上预测深度。这种表示限制了其向任意输出分辨率的扩展能力，并阻碍了几何细节的恢复。本文提出 InfiniDepth，将深度表示为神经隐式场。通过一个简单而有效的局部隐式解码器，我们可以在连续二维坐标处查询深度，从而实现任意分辨率与细粒度的深度估计。为更好地评估本方法的能力，我们从五款不同游戏中构建了一个高质量的 4K 合成基准，涵盖具有丰富几何与外观细节的多样场景。大量实验表明，InfiniDepth 在相对深度估计与度量深度估计任务上，于合成与真实世界基准均取得最优性能，尤其在细节区域表现突出。它还有益于大视角变化下的新视角合成任务，能够以更少的空洞与伪影生成高质量结果。代码与数据将公开。
英文原文摘要 1088 字符
Existing depth estimation methods are fundamentally limited to predicting depth on discrete image grids. Such representations restrict their scalability to arbitrary output resolutions and hinder the geometric detail recovery. This paper introduces InfiniDepth, which represents depth as neural implicit fields. Through a simple yet effective local implicit decoder, we can query depth at continuous 2D coordinates, enabling arbitrary-resolution and fine-grained depth estimation. To better assess our method's capabilities, we curate a high-quality 4K synthetic benchmark from five different games, spanning diverse scenes with rich geometric and appearance details. Extensive experiments demonstrate that InfiniDepth achieves state-of-the-art performance on both synthetic and real-world benchmarks across relative and metric depth estimation tasks, particularly excelling in fine-detail regions. It also benefits the task of novel view synthesis under large viewpoint shifts, producing high-quality results with fewer holes and artifacts. Code and data will be made publicly available.