Abstract In recent years, autonomous driving has garnered escalating attention for its potential to relieve drivers’ burdens and improve driving safety. Vision-based 3D occupancy prediction, which predicts the spatial occupancy status and semantics of 3D voxel grids around the autonomous vehicle from image inputs, is an emerging perception task suitable for cost-effective perception system of autonomous driving. Although numerous studies have demonstrated the greater advantages of 3D occupancy prediction over object-centric perception tasks, there is still a lack of a dedicated review focusing on this rapidly developing field. In this paper, we first introduce the background of vision-based 3D occupancy prediction and discuss the challenges in this task. Second, we conduct a comprehensive survey of the progress in vision-based 3D occupancy prediction from three aspects: feature enhancement, deployment friendliness and label efficiency, and provide an in-depth analysis of the potentials and challenges of each category of methods. Finally, we present a summary of prevailing research trends and propose some inspiring future outlooks. To provide a valuable reference for researchers, a regularly updated collection of related papers, datasets, and codes is organized at github.com/zya3d/Awesome-3D-Occupancy-Prediction website.

Bird's-Eye-View (BEV) representation has emerged as a mainstream paradigm for multi-view 3D object detection, demonstrating impressive perceptual capabilities. However, existing methods overlook the geometric quality of BEV representation, leaving it in a low-resolution state and failing to restore the authentic geometric information of the scene. In this paper, we identify the drawbacks of previous approaches that limit the geometric quality of BEV representation and propose Radial-Cartesian BEV Sampling (RC-Sampling), which outperforms other feature transformation methods in efficiently generating high-resolution dense BEV representation to restore fine-grained geometric information. Additionally, we design a novel In-Box Label to substitute the traditional depth label generated from the LiDAR points. This label reflects the actual geometric structure of objects rather than just their surfaces, injecting real-world geometric information into the BEV representation. In conjunction with the In-Box Label, Centroid-Aware Inner Loss (CAI Loss) is developed to capture the inner geometric structure of objects. Finally, we integrate the aforementioned modules into a novel multi-view 3D object detector, dubbed GeoBEV, which achieves a state-of-the-art result of 66.2% NDS on the nuScenes test set.

Indoor localization systems face critical tradeoffs between accuracy, coverage, robustness, and privacy. Current technologies either achieve high precision at the cost of privacy (camera-based) or preserve privacy while compromising accuracy (signal-based). This limitation is particularly problematic in high-security environments requiring precise tracking within confined spaces (typically 2m × 2m) while prohibiting camera surveillance. We propose WhereRU, a novel multimodal indoor localization system integrating Radio Frequency Identification (RFID) with ultrasonic technologies through a fusion framework. Unlike existing approaches treating modalities as separate components, our system implements deep algorithmic integration where RFID-based coarse-grained localization directly constrains ultrasonic measurements. The system employs WhereNet, a lightweight residual network for RFID processing, achieving 99.74% accuracy at the grid level. This coarse position estimate guides ultrasonic ranging optimization through Limited-memory Broyden-Fletcher-Goldfarb-Shanno Bound (L-BFGS-B) algorithm, effectively mitigating edge-region inaccuracies typical in ultrasonic-only systems. Experimental results demonstrate that WhereRU achieves an average localization error of only 0.107 meters–representing an 81.86% improvement over traditional Time of Arrival methods–while maintaining complete privacy by eliminating biometric data collection. This approach provides a practical solution for secure facilities requiring both centimeter-level localization accuracy and strict privacy preservation.

Recently, the pure camera-based Bird’s-Eye-View (BEV) perception provides a feasible solution for economical autonomous driving. However, the existing BEV-based multiview 3D detectors generally transform all image features into BEV features, without considering the problem that the large proportion of background information may submerge the object information. In this paper, we propose Semantic-Aware BEV Pooling (SA-BEVPool), which can filter out background information according to the semantic segmentation of image features and transform image features into semantic-aware BEV features. Accordingly, we propose BEV-Paste, an effective data augmentation strategy that closely matches with semantic-aware BEV feature. In addition, we design a Multi-Scale Cross-Task (MSCT) head, which combines task-specific and cross-task information to predict depth distribution and semantic segmentation more accurately, further improving the quality of semantic-aware BEV feature. Finally, we integrate the above modules into a novel multi-view 3D object detection framework, namely SA-BEV Experiments on nuScenes show that SA-BEV achieves state-of-the-art performance. Code has been available at https://github.com/mengtan00/SA-BEV.git.