ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera

TL;DR

ET-Former is an end-to-end method that uses a novel triplane deformable attention mechanism and CVAE to improve 3D semantic scene completion from monocular images, achieving state-of-the-art accuracy with low memory use.

Contribution

The paper introduces a triplane deformable attention mechanism and uncertainty estimation via CVAE for monocular 3D scene completion, advancing geometric understanding and efficiency.

Findings

Achieves highest IoU and mIoU scores on Semantic-KITTI dataset.

Reduces GPU memory usage compared to previous methods.

Improves SOTA IoU from 44.71 to 51.49.

Abstract

We introduce ET-Former, a novel end-to-end algorithm for semantic scene completion using a single monocular camera. Our approach generates a semantic occupancy map from single RGB observation while simultaneously providing uncertainty estimates for semantic predictions. By designing a triplane-based deformable attention mechanism, our approach improves geometric understanding of the scene than other SOTA approaches and reduces noise in semantic predictions. Additionally, through the use of a Conditional Variational AutoEncoder (CVAE), we estimate the uncertainties of these predictions. The generated semantic and uncertainty maps will help formulate navigation strategies that facilitate safe and permissible decision making in the future. Evaluated on the Semantic-KITTI dataset, ET-Former achieves the highest Intersection over Union (IoU) and mean IoU (mIoU) scores while maintaining the lowest GPU memory usage, surpassing state-of-the-art (SOTA) methods. It improves the SOTA scores of IoU from 44.71 to 51.49 and mIoU from 15.04 to 16.30 on SeamnticKITTI test, with a notably low training memory consumption of 10.9 GB. Project page: https://github.com/jingGM/ET-Former.git.