Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction

TL;DR

This paper introduces SGCDet, a multi-view indoor 3D object detection framework that adaptively constructs 3D volumes using geometry-aware aggregation and selective voxel refinement, achieving state-of-the-art results without scene geometry supervision.

Contribution

The paper proposes a novel adaptive 3D volume construction method with geometry and context-aware aggregation, improving 3D object detection performance and efficiency.

Findings

Achieves state-of-the-art results on ScanNet, ScanNet200, and ARKitScenes datasets.

Reduces redundant computation by selectively refining high-occupancy voxels.

Operates effectively without relying on ground-truth scene geometry.

Abstract

This work presents SGCDet, a novel multi-view indoor 3D object detection framework based on adaptive 3D volume construction. Unlike previous approaches that restrict the receptive field of voxels to fixed locations on images, we introduce a geometry and context aware aggregation module to integrate geometric and contextual information within adaptive regions in each image and dynamically adjust the contributions from different views, enhancing the representation capability of voxel features. Furthermore, we propose a sparse volume construction strategy that adaptively identifies and selects voxels with high occupancy probabilities for feature refinement, minimizing redundant computation in free space. Benefiting from the above designs, our framework achieves effective and efficient volume construction in an adaptive way. Better still, our network can be supervised using only 3D bounding boxes, eliminating the dependence on ground-truth scene geometry. Experimental results demonstrate that SGCDet achieves state-of-the-art performance on the ScanNet, ScanNet200 and ARKitScenes datasets. The source code is available at https://github.com/RM-Zhang/SGCDet.