ShelfOcc：超越激光雷达的原生三维监督用于基于视觉的占用估计
ShelfOcc: Native 3D Supervision beyond LiDAR for Vision-Based Occupancy Estimation
把视觉三维几何基础模型的输出经跨帧静态几何累积与动态内容剔除，蒸馏成度量一致的语义体素伪标签，可直接替换现有占用模型的 LiDAR 监督信号，为无 LiDAR 的三维场景理解提供可复用的数据侧监督管线。
原文依据 generating metrically consistent semantic voxel labels from video, enabling true 3D supervision without any additional sensors
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期在自监督与弱监督占用估计方面的进展，在很大程度上依赖二维投影或基于渲染的监督，这类方法存在几何不一致和严重的深度渗漏问题。为此，我们提出 ShelfOcc，一种仅依赖视觉、无需激光雷达即可克服上述局限的方法。ShelfOcc 将监督引入原生三维空间，从视频中生成度量一致的语义体素标签，从而在不需要任何额外传感器或人工三维标注的情况下实现真正的三维监督。尽管近期的视觉三维几何基础模型提供了有前景的先验知识来源，但由于几何稀疏、含噪且不一致，尤其是在动态驾驶场景中，它们无法开箱即用地作为预测结果使用。我们的方法引入了一个专门的框架来缓解这些问题：通过跨帧一致地过滤与累积静态几何、处理动态内容，并将语义信息传播到稳定的体素表示中。这种面向弱监督/货架监督占用估计的以数据为中心的监督转变，使得可以使用几乎任何最先进的占用模型架构，而无需依赖激光雷达数据。我们认为，这种高质量监督对于稳健的占用学习至关重要，并且构成了对架构创新的重要补充路径。在 Occ3D-nuScenes 基准上，ShelfOcc 显著优于所有先前的弱监督/货架监督方法（相对提升最高达 34%），为无激光雷达的三维场景理解开辟了一条新的数据驱动方向。
英文原文摘要 1578 字符
Recent progress in self- and weakly supervised occupancy estimation has largely relied on 2D projection or rendering-based supervision, which suffers from geometric inconsistencies and severe depth bleeding.We thus introduce ShelfOcc, a vision-only method that overcomes these limitations without relying on LiDAR.ShelfOcc brings supervision into native 3D space by generating metrically consistent semantic voxel labels from video, enabling true 3D supervision without any additional sensors or manual 3D annotations.While recent vision-based 3D geometry foundation models provide a promising source of prior knowledge, they do not work out of the box as a prediction due to sparse or noisy and inconsistent geometry, especially in dynamic driving scenes.Our method introduces a dedicated framework that mitigates these issues by filtering and accumulating static geometry consistently across frames, handling dynamic content and propagating semantic information into a stable voxel representation.This data-centric shift in supervision for weakly/shelf-supervised occupancy estimation allows the use of essentially any SOTA occupancy model architecture without relying on LiDAR data.We argue that such high-quality supervision is essential for robust occupancy learning and constitutes an important complementary avenue to architectural innovation.On the Occ3D-nuScenes benchmark, ShelfOcc substantially outperforms all previous weakly/shelf-supervised methods (up to a 34% relative improvement), establishing a new data-driven direction for LiDAR-free 3D scene understanding.