3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal task for autonomous driving, as it involves predicting per-voxel occupancy within a 3D scene from partial LiDAR or image inputs. Existing methods primarily focus on the voxel-wise feature aggregation, while neglecting the instance-centric semantics and broader context. In this paper, we present a novel paradigm termed Symphonies (Scene-from-Insts) for SSC, which completes the scene volume from a sparse set of instance queries derived from the input with context awareness. By incorporating the queries as the instance feature representations within the scene, Symphonies dynamically encodes the instance-centric semantics to interact with the image and volume features while avoiding the dense voxel-wise modeling. Simultaneously, it orchestrates a more comprehensive understanding of the scenario by capturing context throughout the entire scene, contributing to alleviating the geometric ambiguity derived from occlusion and perspective errors. Symphonies achieves a state-of-the-art result of 13.02 mIoU on the challenging SemanticKITTI dataset, outperforming existing methods and showcasing the promising advancements of the paradigm. The code is available at \url{https://github.com/hustvl/Symphonies}.

翻译：3D语义场景补全（SSC）已成为自动驾驶领域一项新兴且关键的任务，其目标是从部分激光雷达或图像输入中预测3D场景内的逐体素占用情况。现有方法主要关注体素级特征聚合，却忽视了以实例为中心的语义信息及更广阔的上下文。本文提出一种名为Symphonies（Scene-from-Insts）的全新范式，用于SSC任务，该范式通过从输入中提取的稀疏实例查询（具备上下文感知能力）来补全场集体积。通过将查询作为场景中的实例特征表示，Symphonies动态编码以实例为中心的语义信息，并与图像和体素特征交互，同时避免了密集的体素级建模。与此同时，它通过捕捉整个场景的上下文，协调更全面的场景理解，从而缓解因遮挡和视角误差导致的几何歧义。Symphonies在具有挑战性的SemanticKITTI数据集上取得了13.02 mIoU的最新结果，超越了现有方法，展示了该范式的显著进展。代码开源于\url{https://github.com/hustvl/Symphonies}。