mlsanityData to 14 Oct 2026

Multi-Scale Occ: 4th Place Solution for CVPR 2023 3D Occupancy Prediction Challenge

arXiv 2306.11414 ↗First posted 20 Jun 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In this report, we present the 4th place solution for CVPR 2023 3D occupancy prediction challenge. We propose a simple method called Multi-Scale Occ for occupancy prediction based on lift-splat-shoot framework, which introduces multi-scale image features for generating better multi-scale 3D voxel features with temporal fusion of multiple past frames. Post-processing including model ensemble, test-time augmentation, and class-wise thresh are adopted to further boost the final performance. As shown on the leaderboard, our proposed occupancy prediction method ranks the 4th place with 49.36 mIoU.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 8 of its 21 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

8 of 21 references.

References · 8

  1. 2017Decoupled Weight Decay Regularizationcited by 1,831
  2. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  3. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  4. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  5. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  6. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  7. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  8. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 1.

7 papers.