Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

TL;DR

Symphonies introduces a novel approach for 3D semantic scene completion by integrating instance queries and scene context, significantly improving accuracy in autonomous driving scenarios.

Contribution

The paper proposes Symphonies, a new paradigm that uses instance queries and serial attention mechanisms to enhance 3D scene understanding and address geometric ambiguities.

Findings

Achieves state-of-the-art mIoU scores of 15.04 on SemanticKITTI.

Demonstrates effective integration of instance semantics and scene context.

Improves handling of occlusion and perspective errors in 3D scene completion.

Abstract

`3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal undertaking in autonomous driving, aiming to predict voxel occupancy within volumetric scenes. However, prevailing methodologies primarily focus on voxel-wise feature aggregation, while neglecting instance semantics and scene context. In this paper, we present a novel paradigm termed Symphonies (Scene-from-Insts), that delves into the integration of instance queries to orchestrate 2D-to-3D reconstruction and 3D scene modeling. Leveraging our proposed Serial Instance-Propagated Attentions, Symphonies dynamically encodes instance-centric semantics, facilitating intricate interactions between image-based and volumetric domains. Simultaneously, Symphonies enables holistic scene comprehension by capturing context through the efficient fusion of instance queries, alleviating geometric ambiguity such as occlusion and perspective errors through contextual scene reasoning. Experimental results demonstrate that Symphonies achieves state-of-the-art performance on challenging benchmarks SemanticKITTI and SSCBench-KITTI-360, yielding remarkable mIoU scores of 15.04 and 18.58, respectively. These results showcase the paradigm's promising advancements. The code is available at https://github.com/hustvl/Symphonies.