用神经隐式场实现任意分辨率深度估计，细节更精准。
InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
- 将深度表示为连续坐标可查询的隐式场，突破离散网格限制。
- 在4K合成数据集上超越现有方法，尤其擅长细节区域还原。
- 适合需要高精度深度图的应用，如3D重建与视角合成。
现有深度估计方法受限于离散图像网格的输出，难以扩展至任意分辨率且影响几何细节恢复。本文提出InfiniDepth，将深度表示为神经隐式场，通过简单有效的局部隐式解码器，可在连续2D坐标上查询深度，实现任意分辨率和细粒度深度估计。为评估性能，我们从五个不同游戏构建了一个高质量的4K合成基准，涵盖多样场景及丰富的几何与外观细节。大量实验表明，InfiniDepth在合成与真实世界基准上均达到当前最优表现，尤其在细粒度区域表现突出。该方法还显著提升大视角偏移下的新视角合成质量，生成结果更完整、伪影更少。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。