mlsanityData to 7 Oct 2026

DualPathOcc: Dual-Resolution BEV Encoder for 3D Occupancy Prediction

arXiv 2609.06370 ↗First posted 6 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 37 references that are in the map. First posted on arXiv 6 Sep 2026.

Builds on

37 of 37 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  6. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  7. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  8. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  12. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
25 more
  1. 2019ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networkscited by 572
  2. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  3. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  4. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  5. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  6. 2019Selective Kernel Networkscited by 401
  7. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 357
  8. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  9. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  10. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  11. 2023FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformationcited by 162
  12. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  13. 2023RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervisioncited by 126
  14. 2023PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentationcited by 114
  15. 2023FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugincited by 101
  16. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  17. 2021Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenescited by 89
  18. 2022PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllerscited by 84
  19. 2023Fully Sparse 3D Occupancy Predictioncited by 61
  20. 2024FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird's-Eye View and Perspective Viewcited by 51
  21. 2024Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completioncited by 32
  22. 2023Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completioncited by 21
  23. 2024ProtoOcc: Accurate, Efficient 3D Occupancy Prediction Using Dual Branch Encoder-Prototype Query Decodercited by 17
  24. 2024Deep Height Decoupling for Precise Vision-based 3D Occupancy Predictioncited by 16
  25. 2024Hierarchical Context Alignment with Disentangled Geometric and Temporal Modeling for Semantic Occupancy Predictioncited by 8

Built on by

Not cited yet.