面向自动驾驶的以实例为中心的全景占用预测基准
An Instance-Centric Panoptic Occupancy Prediction Benchmark for Autonomous Driving
为3D全景占用预测提供带实例级真值的高分辨率（0.05 m）物理一致数据集与标准化评测指标，可直接用于训练和公平对比体素级语义+实例联合预测模型，并支撑遮挡推理与几何重建研究。
原文依据 we further construct CarlaOcc, a large-scale, physically consistent panoptic occupancy dataset generated using the CARLA simulator
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论全景占用预测旨在在统一的三维场景表示中联合推断体素级语义与实例身份。然而，该领域的进展仍受限于高质量三维网格资源、实例级标注以及物理一致的占用数据集的缺失。现有基准通常只提供不完整且低分辨率的几何信息，且缺乏实例级标注，这限制了能够实现精确几何重建、可靠遮挡推理与整体三维理解的模型的发展。为应对这些挑战，本文提出了一个面向三维全景占用预测任务的以实例为中心的基准。具体而言，我们引入了 ADMesh，这是首个专为自动驾驶打造的统一三维网格库，集成了超过 15K 个高质量三维模型，具有多样化的纹理与丰富的语义标注。在 ADMesh 的基础上，我们进一步构建了 CarlaOcc，这是一个使用 CARLA 模拟器生成的大规模、物理一致的全景占用数据集。该数据集包含超过 100K 帧，并提供体素分辨率精细至 0.05 m 的细粒度实例级占用真值。此外，我们引入了标准化评测指标，用以量化现有占用数据集的质量。最后，我们在所提出的数据集上建立了代表性模型的系统性基准，为三维全景感知领域的公平比较与可复现研究提供了统一平台。代码与数据集见 https://mias.group/CarlaOcc。
英文原文摘要 1599 字符
Panoptic occupancy prediction aims to jointly infer voxel-wise semantics and instance identities within a unified 3D scene representation. Nevertheless, progress in this field remains constrained by the absence of high-quality 3D mesh resources, instance-level annotations, and physically consistent occupancy datasets. Existing benchmarks typically provide incomplete and low-resolution geometry without instance-level annotations, limiting the development of models capable of achieving precise geometric reconstruction, reliable occlusion reasoning, and holistic 3D understanding. To address these challenges, this paper presents an instance-centric benchmark for the 3D panoptic occupancy prediction task. Specifically, we introduce ADMesh, the first unified 3D mesh library tailored for autonomous driving, which integrates over 15K high-quality 3D models with diverse textures and rich semantic annotations. Building upon ADMesh, we further construct CarlaOcc, a large-scale, physically consistent panoptic occupancy dataset generated using the CARLA simulator. This dataset contains over 100K frames with fine-grained, instance-level occupancy ground truth at voxel resolutions as fine as 0.05 m. Furthermore, standardized evaluation metrics are introduced to quantify the quality of existing occupancy datasets. Finally, a systematic benchmark of representative models is established on the proposed dataset, which provides a unified platform for fair comparison and reproducible research in the field of 3D panoptic perception. Code and dataset are available at https://mias.group/CarlaOcc.