Local Ai
DualPathOcc: Dual-Resolution BEV Encoder for 3D Occupancy Prediction
arXiv:2609.06370v1 Announce Type: new Abstract: Predicting 3D occupancy from multi-view images requires preserving geometric detail during 2D-to-3D lifting while reasoning over sparse, volumetric scen
arXiv:2609.06370v1 Announce Type: new Abstract: Predicting 3D occupancy from multi-view images requires preserving geometric detail during 2D-to-3D lifting while reasoning over sparse, volumetric scene representations. We present DualPathOcc, a camera-based framework that combines a Spatial Enhancer for high-resolution feature aggregation before BEV compression, a SENet-augmented dual-path BEV encoder for local-global context modeling, and height-aware weighted cross-entropy for near-ground occupancy. The final model is optimized with occupancy supervision and no explicit depth loss. On single-frame Occ3D-nuScenes, DualPathOcc achieves 37.37 mIoU. We further analyze how surface-centered depth targets interact with volumetric occupancy learning.
Related
- MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement
- FDR-Occ: Factorized Dense Routing for Full-Spectrum 3D Occupancy Prediction
- GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
Source: arXiv cs.CV | 2026-09-09