Abstract

We introduce SLCF-Net, a novel approach for the Semantic Scene Completion (SSC) task that sequentially fuses LiDAR and camera data. It jointly estimates missing geometry and semantics in a scene from sequences of RGB images and sparse LiDAR measurements. The images are semantically segmented by a pre-trained 2D U-Net and a dense depth prior is estimated from a depth-conditioned pipeline fueled by Depth Anything. To associate the 2D image features with the 3D scene volume, we introduce Gaussian-decay Depth-prior Projection (GDP). This module projects the 2D features into the 3D volume along the line of sight with a Gaussian-decay function, centered around the depth prior. Volumetric semantics is computed by a 3D U-Net. We propagate the hidden 3D U-Net state using the sensor motion and design a novel loss to ensure temporal consistency. We evaluate our approach on the SemanticKITTI dataset and compare it with leading SSC approaches. The SLCF-Net excels in all SSC metrics and shows great temporal consistency.

Qualitative Results

BibTex

@inproceedings{cao2024slcf,

  title = {{SLCF-Net}: Sequential {LiDAR}-Camera Fusion for Semantic Scene Completion using a {3D} Recurrent {U-Net}},

  author = {Cao, Helin and Behnke, Sven},

  booktitle = {IEEE Int. Conf. on Robotics and Automation (ICRA)},

  pages = {2767--2773},

  year = {2024},

}