Dr.Occ: Depth- and Region-Guided 3D Occupancy from Surround-View Cameras for Autonomous Driving
This work addresses perception challenges in autonomous driving by enhancing 3D occupancy prediction, though it appears incremental as it builds on existing methods like BEVDet4D.
The paper tackles geometric misalignment and spatial class imbalance in 3D semantic occupancy prediction for autonomous driving by proposing Dr.Occ, a depth- and region-guided framework, which improves the baseline BEVDet4D by 7.43% mIoU and 3.09% IoU on the Occ3D-nuScenes benchmark.
3D semantic occupancy prediction is crucial for autonomous driving perception, offering comprehensive geometric scene understanding and semantic recognition. However, existing methods struggle with geometric misalignment in view transformation due to the lack of pixel-level accurate depth estimation, and severe spatial class imbalance where semantic categories exhibit strong spatial anisotropy. To address these challenges, we propose Dr.Occ, a depth- and region-guided occupancy prediction framework. Specifically, we introduce a depth-guided 2D-to-3D View Transformer (D$^2$-VFormer) that effectively leverages high-quality dense depth cues from MoGe-2 to construct reliable geometric priors, thereby enabling precise geometric alignment of voxel features. Moreover, inspired by the Mixture-of-Experts (MoE) framework, we propose a region-guided Expert Transformer (R/R$^2$-EFormer) that adaptively allocates region-specific experts to focus on different spatial regions, effectively addressing spatial semantic variations. Thus, the two components make complementary contributions: depth guidance ensures geometric alignment, while region experts enhance semantic learning. Experiments on the Occ3D-nuScenes benchmark demonstrate that \textbf{Dr.Occ} improves the strong baseline BEVDet4D by 7.43\% mIoU and 3.09\% IoU under the full vision-only setting.