GitHub - TUI-NICR/ESANet: ESANet: Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

This repository contains the code to our paper "Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis" (IEEE Xplore, arXiv). This repository contains the code for training, evaluating our networks. Furthermore, we provide code for converting the model to ONNX and TensorRT, as well as for measuring the inference time. The source code is published under BSD 3-Clause license, see license file for details. Note that the preprint was accepted to be published in IEEE International Conference on Robotics and Automation (ICRA).