LiteSense：以 RGB 提升轻量 ToF 实现高分辨率度量深度估计
LiteSense: Lifting Lightweight ToF with RGB for High-Resolution Metric Depth Estimation
用 ToF 的 zone-wise 直方图（CNH）经交叉注意力注入 U-Net 特征，为轻量 RGB-D 网络提供显式度量先验，可作为低成本传感器下高分辨率度量深度估计的可复用融合范式。
原文依据 leverages zone-wise histogram measurements via cross-attention to guide high-level feature fusion
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论度量深度估计旨在从视觉观测中恢复具有绝对尺度、高分辨率且跨场景一致的深度图。现有方法要么依赖大规模模型，要么依赖昂贵的传感器来保持度量精度与泛化能力，二者都不适合资源受限的部署场景。本文提出 LiteSense，一个轻量级 RGB-ToF 融合框架，利用紧凑归一化直方图（CNH）信号与 RGB 线索，实现高效且可靠的度量深度估计。具体而言，LiteSense 采用 U-Net 风格的编码器-解码器，将 RGB 与上采样后的 ToF 深度拼接构成 RGB-D 输入，从而提供显式的度量先验。为应对分辨率差异并恢复细节，我们引入 Patch-wise CNH Spatial Injection（PCSI）模块，通过交叉注意力利用分区直方图测量来引导高层特征融合。在 NYUv2 与 SUN RGB-D 上的大量评估表明，LiteSense 以显著更低的计算成本持续优于单目基线方法与 DELTAR，并展现出良好的零样本泛化能力。我们进一步提出 THDR3K，这是首个室内 RGB-ToF-CNH 数据集；在该数据集上，LiteSense 达到了与 Intel RealSense 相当、并在困难场景下超越后者的真实场景精度。相关源代码与采集的数据集已在 GitHub 公开。
英文原文摘要 1405 字符
Metric depth estimation aims to recover depth maps with absolute scale, high resolution, and cross-scene consistency from visual observations. Existing approaches either rely on large-scale models or costly sensors to preserve metric accuracy and generalization, both ill-suited to resource-constrained deployment. In this paper, we propose LiteSense, a lightweight RGB-ToF fusion framework that leverages compact normalized histogram (CNH) signals together with RGB cues to achieve efficient and reliable metric depth estimation. Specifically, LiteSense leverages a U-Net-style encoder-decoder that forms an RGB-D input by concatenating RGB with upsampled ToF depth, providing explicit metric priors. To address resolution disparity and recover fine details, we introduce the **Patch-wise CNH Spatial Injection (PCSI)** module, which leverages zone-wise histogram measurements via cross-attention to guide high-level feature fusion. Extensively evaluated on NYUv2 and SUN RGB-D, LiteSense consistently outperforms monocular baselines and DELTAR with substantially lower computational cost, and demonstrates promising zero-shot generalization. We further introduce THDR3K, the first indoor RGB-ToF-CNH dataset, where LiteSense achieves real-world accuracy comparable to--and in challenging cases surpassing--Intel RealSense. All the relevant source codes and the collected dataset are available at GitHub.