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.

翻译：在本报告中，我们介绍了面向CVPR 2023 三维占据预测挑战赛的第四名解决方案。我们提出了一种基于“提升-散点-射击”框架的简单方法——多尺度占据（Multi-Scale Occ）。该方法通过引入多尺度图像特征，并结合多个历史帧的时间融合技术，生成更优的多尺度三维体素特征。此外，我们还采用后处理技术（包括模型集成、测试时增强及类别级阈值处理）以进一步提升最终性能。排行榜结果表明，我们所提出的占据预测方法以49.36的mIoU（平均交并比）位列第四名。