Parameter-Free Adaptive Multi-Scale Channel-Spatial Attention Aggregation framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impaired
This work addresses indoor scene understanding for visually impaired users, providing a more reliable and deployable perception framework, though it appears incremental as it builds upon the existing MonoScene pipeline.
The paper tackles the problem of 3D Semantic Scene Completion (SSC) for indoor assistive perception for visually impaired users, where existing monocular approaches suffer from projection diffusion and feature entanglement. The proposed Adaptive Multi-scale Attention Aggregation (AMAA) framework achieves 27.25% SSC mIoU and 43.10% SC IoU on the NYUv2 benchmark, showing consistent improvements over the baseline MonoScene without significantly increasing system complexity.
In indoor assistive perception for visually impaired users, 3D Semantic Scene Completion (SSC) is expected to provide structurally coherent and semantically consistent occupancy under strictly monocular vision for safety-critical scene understanding. However, existing monocular SSC approaches often lack explicit modeling of voxel-feature reliability and regulated cross-scale information propagation during 2D-3D projection and multi-scale fusion, making them vulnerable to projection diffusion and feature entanglement and thus limiting structural stability. To address these challenges, this paper presents an Adaptive Multi-scale Attention Aggregation (AMAA) framework built upon the MonoScene pipeline. Rather than introducing a heavier backbone, AMAA focuses on reliability-oriented feature regulation within a monocular SSC framework. Specifically, lifted voxel features are jointly calibrated in semantic and spatial dimensions through parallel channel-spatial attention aggregation, while multi-scale encoder-decoder fusion is stabilized via a hierarchical adaptive feature-gating strategy that regulates information injection across scales. Experiments on the NYUv2 benchmark demonstrate consistent improvements over MonoScene without significantly increasing system complexity: AMAA achieves 27.25% SSC mIoU (+0.31) and 43.10% SC IoU (+0.59). In addition, system-level deployment on an NVIDIA Jetson platform verifies that the complete AMAA framework can be executed stably on embedded hardware. Overall, AMAA improves monocular SSC quality and provides a reliable and deployable perception framework for indoor assistive systems targeting visually impaired users.